Search

Artificial intelligence (AI) is a science and engineering discipline that is highly relevant to financial services, given the significant amount and diversity of data generated (and consumed) as those services are delivered worldwide. Global banks process billions of international payments each day, while equity exchanges handle trillions of orders and billions of transactions. All of this activity is recorded as data, and driven by exogenous information sources such as news services and social media. To address these challenges, at J.P. Morgan, we established a new group dedicated to research at the intersection of AI and finance in mid-2018 to investigate how to develop and optimize the use of AI. In this article, we introduce and discuss the directions of focus of AI Research and present a few selective projects that illustrate potential novel applications to finance.

While Twitter has become an important platform for generating and disseminating breaking news stories, it is also a medium for spreading false rumors. Most research relevant to newsworthy rumors has treated its subject as a homogeneous class without due consideration to the nuances that distinguish rumors from each other. Some studies, for example, have studied rumor propagation as if all rumors follow the same type of distribution. We question this belief and argue that rumors differ in how they engage their audience, how they spread and by whom, what type of users interact with them, and how they evolve over time. In this paper, we study various semantic aspects of false rumors and analyze their spread. We study the characteristics of rumor usage, emphasize the role users play in rumors, their beliefs, and interactions. Finally, we answer several research questions with regards to each of the topics addressed.

Contains fulltext : 246472.pdf (Publisher’s version ) (Closed access) This study explores the protective effects of family cohesion and school belongingness against the negative consequences of bullying. 481 immigrant and nonimmigrant US middle-school students (Mage = 13.28(0.87), 49% female; 36% ethnic minority) self-reported their experiences being bullied, school belongingness, family cohesion, and socioemotional well-being measured as externalizing, internalizing, and prosocial behaviors. First- or second-generation immigrant youth (n = 72) came from 30 countries in Europe, Asia, Africa, South America, and the Caribbean. Family cohesion served as a protective factor for both immigrant and nonimmigrant youth, but for different outcomes of bullying experiences. For immigrant youth who experienced more bullying, having a more cohesive family was associated with decreased levels of internalizing problems. Additionally, stronger school belongingness and especially family cohesion related to more prosocial behaviors among more frequently bullied immigrant youth. Nonimmigrant youth who experienced bullying, however, reported fewer externalizing problems when they had stronger family cohesion and especially school belongingness. The findings highlight the importance of considering the interacting systems in which immigrant youth are embedded and suggest that family cohesion as a protective factor may work differently for immigrant than for nonimmigrant youth experiencing bias-based bullying. 19 p.

The sheer volume of financial statements makes it difficult for humans to access and analyze a business's financials. Robust numerical reasoning likewise faces unique challenges in this domain. In this work, we focus on answering deep questions over financial data, aiming to automate the analysis of a large corpus of financial documents. In contrast to existing tasks on general domain, the finance domain includes complex numerical reasoning and understanding of heterogeneous representations. To facilitate analytical progress, we propose a new large-scale dataset, FinQA, with Question-Answering pairs over Financial reports, written by financial experts. We also annotate the gold reasoning programs to ensure full explainability. We further introduce baselines and conduct comprehensive experiments in our dataset. The results demonstrate that popular, large, pre-trained models fall far short of expert humans in acquiring finance knowledge and in complex multi-step numerical reasoning on that knowledge. Our dataset -- the first of its kind -- should therefore enable significant, new community research into complex application domains. The dataset and code are publicly available\url{https://github.com/czyssrs/FinQA}., EMNLP 2021

Fine-tuning a pre-trained neural language model with a task specific output layer is the de facto approach of late when dealing with document classification. This technique is inadequate when labeled examples are unavailable at training time and when the metadata artifacts in a document must be exploited. We address these challenges by generating document representations that capture both text and metadata in a task agnostic manner. Instead of traditional auto-regressive or auto-encoding based training, our novel self-supervised approach learns a soft-partition of the input space when generating text embeddings by employing a pre-learned topic model distribution as surrogate labels. Our solution also incorporates metadata explicitly rather than just augmenting them with text. The generated document embeddings exhibit compositional characteristics and are directly used by downstream classification tasks to create decision boundaries from a small number of labels, thereby eschewing complicated recognition methods. We demonstrate through extensive evaluation that our proposed cross-model fusion solution outperforms several competitive baselines on multiple domains.

Information visualization is critical to analytical reasoning and knowledge discovery. We present an interactive studio that integrates perceptive visualization techniques with powerful text analytics algorithms to assist humans in sense-making of large complex text corpora. The novel visual representations introduced here encode the features delivered by modern text mining models using advanced metaphors such as hypergraphs, nested topologies and tessellated planes. They enhance human-computer interaction experience for various tasks such as summarization, exploration, organization and labeling of documents. We demonstrate the ability of the visuals to surface the structure, relations and concepts from documents across different domains.

Many business applications involve adversarial relationships in which both sides adapt their strategies to optimize their opposing benefits. One of the key characteristics of these applications is the wide range of strategies that an adversary may choose as they adapt their strategy dynamically to sustain benefits and evade authorities. In this paper, we present a novel way of approaching these types of applications, in particular in the context of Anti-Money Laundering. We provide a mechanism through which diverse, realistic and new unobserved behavior may be generated to discover potential unobserved adversarial actions to enable organizations to preemptively mitigate these risks. In this regard, we make three main contributions. (a) Propose a novel behavior-based model as opposed to individual transactions-based models currently used by financial institutions. We introduce behavior traces as enriched relational representation to represent observed human behavior. (b) A modelling approach that observes these traces and is able to accurately infer the goals of actors by classifying the behavior into money laundering or standard behavior despite significant unobserved activity. And (c) a synthetic behavior simulator that can generate new previously unseen traces. The simulator incorporates a high level of flexibility in the behavioral parameters so that we can challenge the detection algorithm. Finally, we provide experimental results that show that the learning module (automated investigator) that has only partial observability can still successfully infer the type of behavior, and thus the simulated goals, followed by customers based on traces - a key aspiration for many applications today., A version appeared in the Proceedings of the 2020 ACM International Conference on AI in Finance (ICAIF'20)

BACKGROUND As care-giver’splay an integral role for patients as disease progresses, it is necessary to assess their knowledge and understanding of palliative care to ensure meaningful uptake before developing an appropriate palliative care program.METHODS A cross-sectional survey was conducted. Data was collected from the Aga Khan University Hospital in-patient and out-patient departments and home-based palliative care services from mid 2015 to 2016. All adult care-giver’swho met the inclusion criteria and consented completed a questionnaire till the sample size was reached.Univariate and multivariable analysis and results were reported as crude prevalence’s, crude and adjusted prevalence ratios with 95% confidence intervals using Cox-proportional hazard algorithm. Mean difference of knowledge and attitude scores by care-giver variables was assessed using one-way ANOVA. SPSS version 18 was used and a p-value of less than 5 percent was treated as significant.RESULTS Out of 250 care givers more than 60% were 40 years or less and the majority were males and at least graduates. Approximately 70% of the respondents agreed with the opinion that the person suffering from cancer should be informed about the diagnosis and disease progression. About forty five percent (95% C.I.: 39.03%, 51.37%) of the study respondents had enhanced understandingabout palliative care. Individuals aged

High quality of graphene is necessary for its applications at industrial scale production. The most convenient way is its direct growth on dielectrics which avoid the transfer route of graphene from metal to dielectric substrate usually followed by graphene community. The choice of a suitable dielectric for the gate material which can replace silicon dioxide (SiO2) is in high demand. Various properties like permittivity, thermodynamic stability, film morphology, interface quality, bandgap and band alignment of other dielectrics with graphene needs more exploration. A potential dielectric material is required which could be used to grow graphene with all these qualities. Direct growth of graphene on magnesium oxide (MgO) substrates is an interesting idea and will be a new addition in the library of 2D materials. The present work is about the direct growth of graphene on MgO substrates by an ambient pressure chemical vapour deposition (CVD) method. We address the surface instability issue of the polar oxides which is the most challenging factor in MgO. Atomic force microscopy (AFM) measurements showed the topographical features of the graphene coated on MgO. X-ray photoelectron spectroscopy (XPS) study is carried out to extract information regarding the presence of necessary elements, their bonding with substrates and to confirm the sp-2 hybridization of carbon, which is a characteristic feature of graphene film. The chemical shift is due to the surface reconstruction of MgO in the prepared samples. For graphene-MgO interface, valence band offset (VBO) and conduction band offset (CBO) extracted from valence band spectra reported. Further, we predicted the energy band diagram for single layer and thin film of graphene. By using the room-temperature energy band gap values of MgO and graphene, the CBO is calculated to be 6.85 eV for single layer and 5.66 eV for few layer (1–3) of graphene layers.

BACKGROUND It is necessary to assess carer's understanding of palliative care. The objectives of this study were to ascertain the attitudes and perceptions about the concept and components of palliative care. METHODS A cross-sectional survey was conducted. Data was collected from the Aga Khan University Hospital in-patient and out-patient departments and home-based palliative care services from mid 2015 to 2016. All adult care-givers who met the inclusion criteria and gave informed consent were approached by trained data collectors till the sample size was reached.Univariate and multivariable analysis and results were reported as crude prevalence’s, crude and adjusted prevalence ratios with 95% confidence intervals using Cox-proportional hazard algorithm. Mean difference of knowledge and attitude scores by care giver variables was assessed using one-way ANOVA. SPSS version 18 was used and a p-value of less than 5 percent was treated as significant. RESULTS Out of 250 care givers more than 60% were 40 years or less and the majority were males. Majority were at least graduates. Approximately 70% of the respondents agreed with the opinion that the person suffering from cancer should be informed about the diagnosis and disease progression. About forty five percent (95% C.I.: 39.03%, 51.37%) of the study respondents had correct knowledge about palliative care. Age and relationship with patient had the most variation in response in terms of significance. CONCLUSION Young individuals aged

Internet of Things integrates sensors, actuators, gateways, cloud and applications to create advanced control systems thereby minimizing human interaction in the system. This technology fuses digital devices into our daily lives, creating a huge social and economic impact thus emerging as a major disruptive technology. An architectural framework used in this technology permits integration of very large number of devices. The architectural necessity is to achieve better interoperability, device management, communication, connectivity, data collection mechanisms, security and scalability. This paper provides a synopsis of various layered and system architectures that have been proposed in literature with some hardware and software elements for the implementation of a complete Internet of Things ecosystem. The paper pattern of introducing conventional architectures with the hardware and software components, strengthen the idea of the architectural requirements of Internet of Things. It further reviews the research perspective and the industrial perspective of implementing Internet of Things architectural reference models. The problem solving approaches of novel research and industrial architectural models such as IoTA, IIRA, WSO2 and CISCO are described and compared on the basis of their architectural descriptions. Finally, it discusses the longevity of the reference architectures to converge to a widely acceptable Internet of Things architectural reference model.

Internet of Things integrates objects with unique addressing schemes to their digital processing platforms via communicating network to create advanced control application systems with minimum human interaction. Internet of Things network is expected to have a device/object base of around 212 billion by the year 2020. Such a huge base of devices demands special security mechanisms. The security lags of the hardware and software components of the devices involved comprise to the overall security threat to the Internet of Things paradigm. Internet of Things in its basic form is a three-layered architecture, having physical, network and application layers. This paper discusses the potential attacks on the Internet of Things at each layer of its basic architecture while providing insights about their severity and impact over an Internet of Things network. The paper further elaborates on solutions about the physical security of the Internet of Things devices under a constrained environment and the need for security in the network section where protocols for routing and encryption are implemented. The paper also reviews the solutions at the application level focusing on the valid access to data available on mobile and web interface. Finally, the paper concludes with the discussion regarding the current security scenario and future directions.

The automatic extraction of breaking news events from natural language text is a valuable capability for decision support systems. Traditional systems tend to focus on extracting events from a single media source and often ignore cross-media references. Here, we describe a large-scale automated system for extracting natural disasters and critical events from both newswire text and social media. We outline a comprehensive architecture that can identify, categorize and summarize seven different event types - namely floods, storms, fires, armed conflict, terrorism, infrastructure breakdown, and labour unavailability. The system comprises fourteen modules and is equipped with a novel coreference mechanism, capable of linking events extracted from the two complementary data sources. Additionally, the system is easily extensible to accommodate new event types. Our experimental evaluation demonstrates the effectiveness of the system.

Twitter has become an important online source for real-time news dissemination. Especially, official accounts of local government and media outlets have provided newsworthy and authoritative information, revealing local trends and breaking news. In this paper, we describe TipMaster an automatically constructed knowledge base of Twitter accounts that are likely to report local news, from government agencies to local media outlets. First, we implement classifiers for detecting these accounts by integrating heterogeneous information from the accounts' textual metadata, profile images, and their tweet messages. Next, we demonstrate two use cases for TipMaster: 1) as a platform that monitors real-time social media messages for local breaking news, and 2) as an authoritative source for verifying nascent rumors. Experimental results show that our account classification algorithms achieve both high precision and recall (around 90%). The demonstrated case studies prove that our platform is able to detect local breaking news or debunk emergent rumors faster than mainstream media sources.

Objective The goal of this study was to determine the frequency and factors associated with adult immunization in patients visiting family medicine clinics at a tertiary care hospital in Karachi. Methods A cross-sectional study was conducted from March 2014 to March 2015 in a tertiary care hospital in Karachi, Pakistan. Participants more than 18 years were invited to participate in the study. A pretested questionnaire was used to collect information. Data were entered and analyzed using IBM SPSS Statistics for Windows, version 19.0 (Armonk, NY: IBM Corp). Results A total of 340 patients were surveyed. The majority of patients were female (69.5%) with a mean age of 35.47 years. The majority were married (61.1%), and 30% of the participants had completed graduation or postgraduate education (20%). Most of the patients believed that vaccines can be used in adults to prevent disease (62.2%). Patients believed that the hepatitis B vaccine, influenza vaccine, and hepatitis A vaccine can be administered to adults (58.1%, 29.9%, 33.8%, respectively). The major sources of their information regarding vaccination in adults were friends or relatives (25%) and media (23.2%). Regarding availability of vaccines, 71.3% thought a hepatitis B vaccine is available, 54.9% thought a tuberculosis vaccine is available, and 49.3% thought a tetanus toxoid vaccine is available. Only 36.4% respondents received any vaccine in adulthood. The majority of patients (62.2%) received the hepatitis B vaccine in adulthood. The major reason given for not receiving vaccines was lack of awareness (62.4%). Conclusion Low adult vaccination coverage rates and awareness, as highlighted by the results of this study, show the dire need to address this major preventive strategy. This information can be utilized to conduct larger community-based surveys, to conduct health awareness sessions in the community, and to educate our doctors regarding the availability and benefits of adult vaccines.

In this paper, we present a new approach for detecting novel events from social media, specially Twitter, at real-time. An event is usually defined by who, what, where and when, and an event tweet usually contains terms corresponding to these aspects. To exploit this information, we propose a method that incorporates simple semantics by splitting the tweet term space into groups of terms that have the meaning of the same type. These groups are called semantic categories (classes) and each reflects one or more event aspects. The semantic classes include named entity, mention, location, hashtag, verb, noun and embedded link. To group tweets talking about the same event into the same cluster, similarity measuring is conducted by calculating class-wise similarity and then aggregating them together. Users of a real-time event detection system are usually only interested in novel (new) events, which are happening now or just happened a short time ago. To fulfill this requirement, a temporal identification module is used to filter out event clusters that are about old stories. The clustering module also computes a novelty score for each event cluster, which reflects how novel the event is, compared to previous events. We evaluated our event detection method using multiple quality metrics and a large-scale event corpus having millions of tweets. The experiment results show that the proposed online event detection method achieves the state-of-the-art performance. Our experiment also shows that the temporal identification module can effectively detect old events.

Background Nocturnal enuresis (NE) is a common symptom in children worldwide. International Children’s Continence Society (ICCS) defines enuresis as either mono-symptomatic, NE with lower urinary tract symptoms and NE with co-morbid conditions. The objectives of this study were to determine the frequencies and types of NE and associated symptoms and conditions in children aged 5 to 16 years based on ICCS criteria. Methods A multi-center cross sectional study was conducted between November 2012 and December 2013 in the primary care clinics of four hospitals in Karachi. Children aged five to fifteen years were included through consecutive sampling. Informed consent was obtained from the parents and a pre-coded semi-structured questionnaire was used to obtain the information. Data was entered on SPSS version 20.0 and multivariable logistic regression analysis was used for data analysis. Results Out of 429 children aged between five and sixteen years, 243(56.9%) were boys and the remaining 186(43.1%) were girls. One hundred and eighty three children (43%) had nocturnal enuresis (NE). Forty four (10.3%), had mono-symptomatic NE, 57(31.1%) had associated lower urinary tract symptoms (NE-LUTS), whereas 30 (16.3%) had NE with a co-morbid condition. Fifty two (28.4%) NE’s had at least one of both LUTS and a co-morbid condition. Out of the 246(57%) non-enuretic’s, 31(12.6%) had a LUTS, 95(38.6%) had a co-morbid condition and 57(23.2%) had at least one of both LUTS and a co-morbid condition. The remaining 63 (25.6%) were symptom free. Increased voiding frequency, urgency, dysuria, suprapubic pain and daytime incontinence were the LUTS significantly associated with NE. Co-morbid conditions significantly associated with NE included constipation, congenital defects, developmental delay, and learning and sleep problems. Conclusion Although NE can be an only symptom, it is often associated with lower urinary tract symptoms like dysuria, urgency, suprapubic pain, and daytime incontinence. Children presenting with NE often have co-morbid conditions like constipation, urinary tract infection, sleep disorders, and developmental delay. Many children presenting with these conditions as the primary complaint may also have NE. It should be addressed as unrecognized and untreated NE can cause additional morbidity and distress.

Previous studies have shown that investor sentiment indicators can predict stock market change. A domain-specific sentiment lexicon and sentiment-oriented word embedding model would help the sentiment analysis in financial domain and stock market. In this paper, we present a new approach to learning stock market lexicon from StockTwits, a popular financial social network for investors to share ideas. It learns word polarity by predicting message sentiment, using a neural net-work. The sentiment-oriented word embeddings are learned from tens of millions of StockTwits posts, and this is the first study presenting sentiment-oriented word embeddings for stock market. The experiments of predicting investor sentiment show that our lexicon outperformed other lexicons built by the state-of-the-art methods, and the sentiment-oriented word vector was much better than the general word embeddings.

To deal with the sheer volume of information and gain competitive advantage, the news industry has started to explore and invest in news automation. In this paper, we present Reuters Tracer, a system that automates end-to-end news production using Twitter data. It is capable of detecting, classifying, annotating, and disseminating news in real time for Reuters journalists without manual intervention. In contrast to other similar systems, Tracer is topic and domain agnostic. It has a bottom-up approach to news detection, and does not rely on a predefined set of sources or subjects. Instead, it identifies emerging conversations from 12+ million tweets per day and selects those that are news-like. Then, it contextualizes each story by adding a summary and a topic to it, estimating its newsworthiness, veracity, novelty, and scope, and geotags it. Designing algorithms to generate news that meets the standards of Reuters journalists in accuracy and timeliness is quite challenging. But Tracer is able to achieve competitive precision, recall, timeliness, and veracity on news detection and delivery. In this paper, we reveal our key algorithm designs and evaluations that helped us achieve this goal, and lessons learned along the way., Comment: Accepted by IEEE Big Data 2017

Social media hashtags are useful in many applications, such as tweet classification, clustering, searching, indexing, and social network analysis. In this chapter, we present a Big Data mining technology on social media, and demonstrate how to use it to address the following three problems: discovering relevant hashtags for health concepts, discovering the meaning of health-related hashtags, and identifying hashtags relevant to each other in the health domain. The proposed approach is based on the distributed word representations, which are learned, by applying the state-of-the-art deep learning technology, from billions of tweet words without supervision. The experiment shows that this approach outperformed the baseline approach. To the best of our knowledge, this is the first study of applying distributed language representations to discovering relationships between health concepts and hashtags.

This paper describes the approach we used for SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs. We use three types of word embeddings in our algorithm: word embeddings learned from 200 million tweets, sentiment-specific word embeddings learned from 10 million tweets using distance supervision, and word embeddings learned from 20 million StockTwits messages. In our approach, we also take the left and right context of the target company into consideration when generating polarity prediction features. All the features generated from different word embeddings and contexts are integrated together to train our algorithm

This paper describes the approach we used for SemEval-2017 Task 4: Sentiment Analysis in Twitter. Topic-based (target-dependent) sentiment analysis has become attractive and been used in some applications recently, but it is still a challenging research task. In our approach, we take the left and right context of a target into consideration when generating polarity classification features. We use two types of word embeddings in our classifiers: the general word embeddings learned from 200 million tweets, and sentiment-specific word embeddings learned from 10 million tweets using distance supervision. We also incorporate a text feature model in our algorithm. This model produces features based on text negation, tf.idf weighting scheme, and a Rocchio text classification method. We participated in four subtasks (B, C, D & E for English), all of which are about topic-based message polarity classification. Our team is ranked #6 in subtask B, #3 by MAEu and #9 by MAEm in subtask C, #3 using RAE and #6 using KLD in subtask D, and #3 in subtask E.

Tables are significant document components. Table extraction and classification are critical for us to explore, retrieve and mine knowledge encoded in tables. This paper presents a learning based approach for classifying tables based on their content and structural information, with focus on financial document tables. To the best of our knowledge, this is the first study on classifying tables in financial domain, and also the first study of table classification based on its semantics, a more fine-grained level than previous studies. The experimental results show that it can effectively classify financial tables. We also analyzed what features are important and how to generate them. The feature identification and generation approach can potentially apply to other domains.

Two of the major problems in social media message classification are the data sparseness issue and the high degree of lexical variation. Paraphrases, or synonyms, are alternative ways of expressing the same meaning using different lexical variations. In this study, we try to use paraphrases to improve tweet topic classification performance. We explored two approaches to generating paraphrases, WordNet, which is a lexical database grouping English words into sets of synonyms, and word embeddings, which are learned from millions of tweets and billions of words. Our experiment shows that using paraphrases can improve the topic classification task, and the word embedding approach outperforms the WordNet method. To our knowledge, this is the first study exploiting paraphrases for tweet classification.

Internet of things (IoT) employs un-abatable number of intelligent sensing and actuating devices with advanced software stacks to integrate physical and digital world. To address issues of heterogeneity, communication, connectivity, data collection mechanisms, security and scalability, each IoT application is based on some architecture describing data flow through the system. Given to continuous evolution of IoT enabling technologies, it is challenging to standardise one concrete architecture. This paper provides the synopsis of the IoT architectures, discusses the architectural reference framework of IoT-A, Industrial IoT reference architecture, WSO2 and CISCO architectural models that minimise the architectural levels of abstraction and describe an architectural model based on present IoT enabling technologies. It discusses a model to evaluate the architectural criteria addressed by the discussed architectures to arrive at an architectural reference model that has the potential to serve as a standard for collective IoT application development.

In the most basic application of Ant Colony Optimization (ACO), a set of artificial ants find the shortest path between a source and a destination. Ants deposit pheromone on paths they take, preferring paths that have more pheromone on them. Since shorter paths are traversed faster, more pheromone accumulates on them in a given time, attracting more ants and leading to reinforcement of the pheromone trail on shorter paths. This is a positive feedback process that can also cause trails to persist on longer paths, even when a shorter path becomes available. To counteract this persistence on a longer path, ACO algorithms employ remedial measures, such as using negative feedback in the form of uniform evaporation on all paths. Obtaining high performance in ACO algorithms typically requires fine tuning several parameters that govern pheromone deposition and removal. This paper proposes a new ACO algorithm, called EigenAnt, for finding the shortest path between a source and a destination, based on selective pheromone removal that occurs only on the path that is actually chosen for each trip. We prove that the shortest path is the only stable equilibrium for EigenAnt, which means that it is maintained for arbitrary initial pheromone concentrations on paths, and even when path lengths change with time. The EigenAnt algorithm uses only two parameters and does not require them to be finely tuned. Simulations that illustrate these properties are provided.

Load balancers distribute workload across multiple nodes based on a variation of the round robin algorithm, or a more complex algorithm that optimizes a specified objective or allows for horizontal scalability and higher availability. In this paper, we investigate whether robust load balancing can be achieved using a local co-operative mechanism between the resources (nodes). The local aspect of the mechanism implies that each node interacts with a small subset of the nodes that define its neighborhood. The co-operative aspect of the mechanism implies that a node may offload some of load to its neighbor nodes that have lesser load or accept jobs from neighbor nodes that have higher load. Each node is thus only aware of the state of its neighboring nodes and there is no central entity that has the knowledge of the state of all the nodes. We model the overall mechanism of load balancing based on local interactions as a congestion game and show that convergence to the Nash equilibrium is possible using only local interactions. We derive worst case bounds on the number of transfers (time) required to achieve global load balancing under this setup. We also include simulation results to demonstrate emergent global load balancing based only on local interactions and local information.

News professionals are facing the challenge of discovering news from more diverse and unreliable information in the age of social media. More and more news events break on social media first and are picked up by news media subsequently. The recent Brussels attack is such an example. At Reuters, a global news agency, we have observed the necessity of providing a more effective tool that can help our journalists to quickly discover news on social media, verify them and then inform the public. In this paper, we describe Reuters Tracer, a system for sifting through all noise to detect news events on Twitter and assessing their veracity. We disclose the architecture of our system and discuss the various design strategies that facilitate the implementation of machine learning models for noise filtering and event detection. These techniques have been implemented at large scale and successfully discovered breaking news faster than traditional journalism

Classifying tweets into topic categories is necessary and important for many applications, since tweets are about a variety of topics and users are only interested in certain topical areas. Many tweet classification approaches fail to achieve high accuracy due to data sparseness issue. Tweet, as a special type of short text, in additional to its text, also has other metadata that can be used to enrich its context, such as user name, mention, hashtag and embedded link. In this demonstration, we present TweetSift, an efficient and effective real time tweet topic classifier. TweetSift exploits external tweet-specific entity knowledge to provide more topical context for a tweet, and integrates them with topic enhanced word embeddings for topic classification. The demonstration will show how TweetSift works and how it is incorporated with our social media event detection system.

In this paper, we present a new approach of recommending hashtags for tweets. It uses Learning to Rank algorithm to incorporate features built from topic enhanced word embeddings, tweet entity data, hashtag frequency, hashtag temporal data and tweet URL domain information. The experiments using millions of tweets and hashtags show that the proposed approach outperforms the three baseline methods -- the LDA topic, the tf.idf based and the general word embedding approaches.

Social networks enable knowledge sharing that inevitably begs the question of expertise analysis. Many online profiles claim expertise, but possessing true expertise is rare. We characterize expertise as projected expertise (claims of a person), perceived expertise (how the crowd perceives the individual) and true expertise (factual). StockTwits, an investor-focused microblogging platform, allows us to study all three aspects simultaneously. We analyze more than 18 million tweets spanning 1700 days. The large time scale allows us to also analyze expertise and its categories as they evolve over time, which is the first study of its kind on StockTwits. We propose a method to capture perceived expertise by how significantly a user's follower network grows and how often the user is brought up in conversations. We also quantify actual, market-based, true expertise based on the user's trade and investment recommendations. Finally we provide an analysis bringing out the differences between how users project themselves, how the crowd perceives them, and how they are actually performing on the market. Our results show that users who project themselves as experts are ones that talk the most and provide the least recommendation-to-tweet ratio (that is, most of their conversations are mundane). The recommendations from users who project novice expertise slightly outperform (≈5%) the overall stock market. On the other hand, the trade recommendations from self-proclaimed experts yield 80% less than those of intermediate traders. Interestingly, users who are perceived as experts by others, as measured by centrality measurements, resulted in net negative returns after a four year trading period. Our study also looks at the evolution of expertise, and begins to understand why and what makes users change the way they project their own expertise. For this topic, however, this paper introduces more questions than it answers, which will serve as the basis for future studies.

AKDN has one of the most comprehensive private not-for-profit health care systems in the developing world. It has state-of-the-art urban academic tertiary care centers, service hospitals and community based primary care centers spread across the most remote areas of Central and South Asia and East Africa. In response to a global initiative to make palliative care widely available, the AKDN is spearheading the integration of palliative care across its international health network. The scope includes specialist palliative care services in urban tertiary care centers across secondary and outreach programs to home based palliative care services. The ultimate goal is to develop a comprehensive structure of palliative care services which, in addition tofulfilling the vision of quality, also fulfills the needs of the communities that it serves. This article describes the international undertaking; its challenges and the key contextual design principles of the implementation.

We have investigated the initial oxidation of the Rh(113) and Rh(223) vicinal surfaces by STM and ab initio simulations. Upon adsorption of small amounts of oxygen, the surface morphology is completely altered. Surprisingly, oxygen-stabilized Rh adatoms can be observed on the (113) facets, with oxide-like electronic properties. We present models of these "0D oxide" phases and discuss reasons for their stability.

In this paper, we shed light on how powerful congestion control based on local interactions may be obtained. We show how ants can use repellent pheromones and incorporate the effect of crowding to avoid traffic congestion on the optimal path. Based on these interactions, we propose an ant algorithm, the M-unit EigenAnt algorithm, that leads to the selection of the M shortest paths. The ratio of selection of each of these paths is also optimal and regulated by an optimal amount of pheromone on each of them. To the best of our knowledge, the M-unit EigenAnt algorithm is the first antalgorithm that explicitly ensures the selection of the M shortest paths and regulates the amount of pheromone on them such that it is asymptotically optimal. In fact, it is in contrast with most ant algorithms that aim to discover just a single best path. We provide its convergence analysis and show that the steady state distribution of pheromone aligns with the eigenvectors of the cost matrix, and thus is related to its measure of quality. We also provide analysis to show that this property ensues even when the food is moved or path lengths change during foraging. We show that this behavior is robust in the presence of fluctuations and quickly reflects the change in the M optimal solutions. This makes it suitable for not only distributed applications butalso dynamic ones as well. Finally, we provide simulation results for the convergence to the optimal solution under different initial biases, dynamism in lengths of paths, and discovery of new paths.

Faced with a choice of paths, an ant chooses a path with a higher concentration of pheromone. Subsequently, it drops pheromone on the path chosen. The reinforcement of the pheromone-following behavior favors the selection of an initially discovered path as the preferred path. This may cause a long path to emerge as the preferred path, were it discovered earlier than a shorter path. However, the shortness of the shorter path offsets some of the pheromone accumulated on the initially discovered longer path. In this paper, we model the trail formation behavior as a generalized Polya urn process. For k equal length paths, we give the distribution of pheromone at any time and highlight its sole dependence on the initial pheromone concentrations on paths. Additionally, we propose a method to incorporate the lengths of paths in the urn process and derive how the pheromone distribution alters on its inclusion. Analytically, we show that it is possible, under certain conditions, to reverse the initial bias that may be present in favor of paths that were discovered prior to the discovery of more efficient (shorter) paths. This addresses the Plasticity-Stability dilemma for ants, by laying out the conditions under which the system will remain stable or become plastic and change the path. Finally, we validate our analysis and results using simulations.

Rumor events differ in how and where they originate, what topics they address, the emotions they invoke, and how they engage their audience. In this paper, we study various semantic aspects of rumors and analyze the motivational and functional roles they play. Using Twitter as a case study, we develop a framework to characterize rumors. Our characterization covers intrinsic and extrinsic factors, tweet and event-level, as well as usage analysis. We determine the roles various user-types play and analyze rumor propagation from both a re-tweeting and burstiness perspective.

In this paper, we propose the first real time rumor debunking algorithm for Twitter. We use cues from 'wisdom of the crowds', that is, the aggregate 'common sense' and investigative journalism of Twitter users. We concentrate on identification of a rumor as an event that may comprise of one or more conflicting microblogs. We continue monitoring the rumor event and generate real time updates dynamically based on any additional information received. We show using real streaming data that it is possible, using our approach, to debunk rumors accurately and efficiently, often much faster than manual verification by professionals.

We propose a novel yet simple method for creating a stock market trading strategy by following successful stock market expert in social media. The problem of “how and where to invest” is translated into “who to follow in my investment”. In other words, looking for stock market investment strategy is converted into stock market expert search. Fortunately, many stock market experts are active in social media and openly express their opinions about market. By analyzing their behavior, and mining their opinions and suggested actions in Twitter, and simulating their recommendations, we are able to score each expert based on his/her performance. Using this scoring system, experts with most successful trading are recommended. The main objective in this research is to identify traders that outperform market historically, and aggregate the opinions from such traders to recommend trades.

We propose a novel approach to label social media text using significant stock market events (big losses or gains). Since stock events are easily quantifiable using returns from indices or individual stocks, they provide meaningful and automated labels. We extract significant stock movements and collect appropriate pre, post and contemporaneous text from social media sources (for example, tweets from twitter). Subsequently, we assign the respective label (positive or negative) for each tweet. We train a model on this collected set and make predictions for labels of future tweets. We aggregate the net sentiment per each day (amongst other metrics) and show that it holds significant predictive power for subsequent stock market movement. We create successful trading strategies based on this system and find significant returns over other baseline methods.

Background: Evidence highlights a lack of communication skills in doctors leading to dysfunctional consultations. To address this deficit, a private medical college instituted curricular reforms with inclusion of a longitudinal communication skills program. A pilot study was undertaken to evaluate the effectiveness of this program by comparing the consultation skills of medical students of this college with a medical college without a communication skills program. Methods: A 4-station Objective Structured Clinical Examination (OSCE) was conducted in the third and final year. Mann–Whitney U-test was used to compare the difference in the distribution between OSCE stations total and construct scores. Results: At the end of the third year, 21 (31.34%), students of the study site (medical college 1 [college with integrated longitudinal communication skills program]) and 31 (46.26%) students from the comparison site (medical college 2 [comparable college without communication skills program]) consented. Medical college 1 achieved a significantly higher overall mean total station score of 68.0% (standard deviation [SD] =13.5) versus 57.2% (SD = 15.4) (P < 0.001). Significantly higher mean scores were achieved on three stations. At the end of the final year, 19 students (29.3%) from medical college 1 and 22 (34%) students from medical college 2 consented. The difference in overall mean total station score reduced from 9.2% to 7.1% (70.2) (SD = 13.7) versus 63.1 (SD = 15.2) (P = 0.004). The mean scores of both colleges decreased in “Patient presenting with Hepatitis C Report” station (P values 0.004 and 0.775) and in “Patient Request for Faith Healing Therapy in Diabetes Mellitus” station (P values 0.0046 and 0.036), respectively. Conclusion: Longitudinal communication skills in an undergraduate curriculum positively impacted consultation skills. Community-based training and faculty development are required to develop effective patient-centered consultation skills.

We investigated the composition of decagonal Al-Co-Cu surface by Auger electron spectroscopy (AES) and low-energy ion scattering (LEIS). The surface composition after annealing was Al richer and Co poorer compared to that after sputtering or bulk composition. Two types of the characteristic clusters were observed by scanning tunneling microscopy (STM) and no bias voltage dependence of the image was observed. On the other hand, scanning tunneling spectroscopy revealed a subtle difference of local density of states in unoccupied states between different sites. Structural optimization using ab initio calculations based on density functional theory (DFT) was performed on several compositional models, which are based on the W-(AlCoNi) bulk model. The surface structures of two types of the characteristic clusters were determined by comparison of the STM image and the simulated image of the structures obtained by DFT. The topmost layer was composed of Al and Cu atoms, and the compositional ratio was consistent with the AES and LEIS results.

Collective foraging in ant colonies is as remarkable in that ants are solving a distributed control and optimization task that is still not fully untravelled. Ants deposit pheromone as they travel, and paths with more pheromone are preferred by succeeding ants. Without any direct communication amongst themselves, ants quickly abandon other trails to concentrate on the shortest one. If the food source moves, or a new path is discovered, ants can still overcome initial bias due to pheromone deposited on an earlier path, and switch to the new path. Nevertheless, important questions remain. How much should be advantage offered by a better path discovered later for the ants to switch to it if an initial preference or bias has already built up on an earlier path ? How much bias is too much ? When multiple food sources are present, ants form multiple trails that seem to optimize overall throughput, if that word may be considered apt. These questions have importance in many real life scenarios. How can information be optimally disseminated ? If a competitors's products or technologies have a large initial bias, then how much gain or advantage should a new product or technology provide in order to cultivate a large following or market share ? What kind of share in the market should you probabilistically expect for the gain you offer ? In the presence of dynamically changing traffic scenarios, how can packets be routed without centralized command and control to maximize network throughput ? This talk summarizes some of our recent work. First, we showed that for traditional ant colony optimization models, beyond a certain threshold, initial bias cannot be overcome. That is, even if a better path is found, ants will not switch from a longer path that has been frequented for a long enough time. Next, motivated by some knowledge of biological ants, we suggest a biologically motivated ant pheromone update model that guarantees convergence to the shortest path regardless of initial bias. The algorithm displays this behaviour even when the food source is moved or path lengths change during foraging. Finally, we examine the utility of such an algorithm in the context of routing in communication networks.

We have grown 22-ML-thick Fe films on a Cu(100) single crystal. The films were stabilized in the face-centered-cubic (fcc) $\ensuremath{\gamma}$ phase by adsorption of carbon monoxide during growth, preventing the transformation to the body-centered-cubic (bcc) $\ensuremath{\alpha}$ phase. A structural transformation of these films from fcc to bcc can be induced by ${\text{Ar}}^{+}$ ion irradiation. Scanning-tunneling microscopy images show the nucleation of bcc crystallites, which grow with increasing ${\text{Ar}}^{+}$ ion dose and eventually result in complete transformation of the film to bcc. Surface magneto-optic Kerr effect measurements confirm the transformation of the Fe film from paramagnetic (fcc) to ferromagnetic (bcc) with an in-plane easy axis. The transformation can also be observed by low-energy electron diffraction. We find only very few nucleation sites of the bcc phase and argue that nucleation of the bcc phase happens under special circumstances during resolidification of the molten iron in the thermal spike after ion impact. Intermixing with the Cu substrate impedes the transformation. We also demonstrate the transformation of films coated with Au to protect them from oxidation at ambient conditions.

We propose a global optimization algorithm called GOSAM (Global Optimization using Support vector regression based Adaptive Multistart) that applies statistical machine learning techniques, viz. Support Vector Regression (SVR) to adaptively direct iterative search in large-scale global optimization. At each iteration, GOSAM builds a training set of the objective function’s local minima discovered till the current iteration, and applies SVR to construct a regressor that learns the structure of the local minima. In the next iteration the search for the local minimum is started from the minimum of this regressor. The idea is that the regressor for local minima will generalize well to the local minima not obtained so far in the search, and hence its minimum would be a ‘crude approximation’ to the global minimum. This approximation improves over time, leading the search towards regions that yield better local minima and eventually the global minimum. Simulation results on well known benchmark problems show that GOSAM requires significantly fewer function evaluations to reach the global optimum, in comparison with methods like Particle Swarm optimization and Genetic Algorithms. GOSAM proves to be relatively more efficient as the number of design variables (dimension) increases. GOSAM does not require explicit knowledge of the objective function, and also does not assume any specific properties. We also discuss some real world applications of GOSAM involving constrained and design optimization problems.

To determine the practices and knowledge of harmful effects regarding use of Chaalia and Pan Masala in three schools of Mahmoodabad and Chanesar Goth, Jamshed Town, Karachi, Pakistan.To achieve the objective a cross-sectional design was used in three government schools of Mahmoodabad and Chanesar Goth, Jamshed Town, Karachi. Students of either gender drawn from these schools fulfilling the inclusion and exclusion criteria were interviewed using a pre-coded structured questionnaire. Along with demographic data, questions regarding frequency of Chaalia and Pan Masala use, practices of this habit in friends and family and place of procurement of these substances, were inquired. Knowledge was assessed about harmful effects and its source of information. In addition, practices in relation to that knowledge were assessed.A total of 370 students were interviewed over a period of six weeks, of which 205 (55.4%) were boys. The ages of the students were between 10 and 15 years. Thirty one percent of the fathers and 62% of the mothers were uneducated. The frequency of use of any brand of Chaalia was found to be 94% and that of Pan Masala was 73.8%. Eighty five percent of them were regular users. A large majority (88%) procured the substances themselves from near their homes. Ninety five percent of the children had friends with the same habits. Eighty four percent were using the substances in full knowledge of their families. Chaalia was considered harmful for health by 96% and Pan Masala by 60%. Good taste was cited as a reason for continuing the habit by 88.5% of the children and use by friends by 57%. Knowledge about established harmful effects was variable. Knowledge about harmful effects was high in both "daily" and "less than daily users".The frequency of habits of Chaalia and Pan Masala chewing, by school children in lower socio-economic areas is extremely high. The probable reasons for this high frequency are taste, the widespread use of these substances by family members and friends, low cost and easy availability.

To determine the practices and knowledge about chhaalia and paan masala chewing among school children in Mahmoodabad and Chanesar Goth, Karachi, Pakistan.A cross-sectional study was conducted in three government schools of Mahmoodabad and Chanesar Goth, Jamshed Town, Karachi. Students of either gender were interviewed using a pre-coded structured questionnaire. In addition to the demographic data, questions included frequency of use, practices among friends and family and procurement of these substances. Knowledge about harmful effects, source of the knowledge and practices in relation to knowledge were also assessed.A total of 370 students, ages between 10 to 15 years were interviewed, of which 205 (55.4%) were boys. Thirty one percent of fathers and 62% of mothers were uneducated. The frequency of using chhaalia was 94% and that of paan masala was 73.8%, with 85% being regular users and 95% had friends with similar habits. Majority (88%) procured the substances near their homes, chhaalia was considered harmful for health by 96% and Paan Masala by 60% of the students. The commonest reason for continuing use was good taste (88.5%) followed by company of friends (57%). Knowledge about harmful effects was adequate in both "daily" and "less than daily users".The frequency of chhaalia and paan masala chewing, among school children in lower socio-economic areas is high. The probable reasons might be the taste, widespread use of these substances by family members and friends, low cost and easy availability. Although knowledge about harmful effects of these habits was adequate, but very little students knew about Oral Submucous Fibrosis (OSMF).

Least Squares Proximal Support Vector Regression (LSPSVR) requires only a single matrix inversion to obtain the Lagrange Multipliers as opposed to solving a Quadratic Programming Problem (QPP) for the conventional SVM optimization problem. However, like other least squares based methods, LSPSVR suffers from lack of sparseness. Most of the Lagrange multipliers are non-zero and thus the determination of the separating hyperplane requires a large number of data points. Large zero norm of Lagrange multipliers inevitably leads to a large kernel matrix that is inappropriate for fast regression on large datasets. This paper suggests how the LSPSVR formulation may be recast into one that also tries to minimize the zero norm of the vector of Lagrange multipliers, and in effect imposes sparseness. Experimental results on benchmark data show that a significant decrease in the number of support vectors can be achieved without a concomitant increase in the error.