Search

User embeddings play a crucial role in user engagement forecasting and personalized services. Recent advances in sequence modeling have sparked interest in learning user embeddings from behavioral data. Yet behavior-based user embedding learning faces the unique challenge of dynamic user modeling. As users continuously interact with the apps, user embeddings should be periodically updated to account for users' recent and long-term behavior patterns. Existing methods highly rely on stateless sequence models that lack memory of historical behavior. They have to either discard historical data and use only the most recent data or reprocess the old and new data jointly. Both cases incur substantial computational overhead. To address this limitation, we introduce User Stateful Embedding (USE). USE generates user embeddings and reflects users' evolving behaviors without the need for exhaustive reprocessing by storing previous model states and revisiting them in the future. Furthermore, we introduce a novel training objective named future W-behavior prediction to transcend the limitations of next-token prediction by forecasting a broader horizon of upcoming user behaviors. By combining it with the Same User Prediction, a contrastive learning-based objective that predicts whether different segments of behavior sequences belong to the same user, we further improve the embeddings' distinctiveness and representativeness. We conducted experiments on 8 downstream tasks using Snapchat users' behavioral logs in both static (i.e., fixed user behavior sequences) and dynamic (i.e., periodically updated user behavior sequences) settings. We demonstrate USE's superior performance over established baselines. The results underscore USE's effectiveness and efficiency in integrating historical and recent user behavior sequences into user embeddings in dynamic user modeling.

Existing works on long-term open-domain dialogues focus on evaluating model responses within contexts spanning no more than five chat sessions. Despite advancements in long-context large language models (LLMs) and retrieval augmented generation (RAG) techniques, their efficacy in very long-term dialogues remains unexplored. To address this research gap, we introduce a machine-human pipeline to generate high-quality, very long-term dialogues by leveraging LLM-based agent architectures and grounding their dialogues on personas and temporal event graphs. Moreover, we equip each agent with the capability of sharing and reacting to images. The generated conversations are verified and edited by human annotators for long-range consistency and grounding to the event graphs. Using this pipeline, we collect LoCoMo, a dataset of very long-term conversations, each encompassing 300 turns and 9K tokens on avg., over up to 35 sessions. Based on LoCoMo, we present a comprehensive evaluation benchmark to measure long-term memory in models, encompassing question answering, event summarization, and multi-modal dialogue generation tasks. Our experimental results indicate that LLMs exhibit challenges in understanding lengthy conversations and comprehending long-range temporal and causal dynamics within dialogues. Employing strategies like long-context LLMs or RAG can offer improvements but these models still substantially lag behind human performance., Comment: 19 pages; Project page: https://snap-research.github.io/locomo

Content moderators play a key role in keeping the conversation on social media healthy. While the high volume of content they need to judge represents a bottleneck to the moderation pipeline, no studies have explored how models could support them to make faster decisions. There is, by now, a vast body of research into detecting hate speech, sometimes explicitly motivated by a desire to help improve content moderation, but published research using real content moderators is scarce. In this work we investigate the effect of explanations on the speed of real-world moderators. Our experiments show that while generic explanations do not affect their speed and are often ignored, structured explanations lower moderators' decision making time by 7.4%., Comment: 11 pages, 14 figures, to be published at ACL 2024

In human-computer interaction, understanding user behaviors and tailoring systems accordingly is pivotal. To this end, general-purpose user representation learning based on behavior logs is emerging as a powerful tool in user modeling, offering adaptability to various downstream tasks such as item recommendations and ad conversion prediction, without the need to fine-tune the upstream user model. While this methodology has shown promise in contexts like search engines and e-commerce platforms, its fit for instant messaging apps, a cornerstone of modern digital communication, remains largely uncharted. These apps, with their distinct interaction patterns, data structures, and user expectations, necessitate specialized attention. We explore this user modeling approach with Snapchat data as a case study. Furthermore, we introduce a novel design and evaluation framework rooted in the principles of the Measurement Process Framework from social science research methodology. Using this new framework, we design a Transformer-based user model that can produce high-quality general-purpose user representations for instant messaging platforms like Snapchat.

Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions. Despite the success in high-resource languages, its application in lower-resource ones faces challenges due to the imbalanced foundational abilities of LLMs across different languages, stemming from the uneven language distribution in their pre-training data. To tackle this issue, we propose pivot language guided generation (PLUG), an approach that utilizes a high-resource language, primarily English, as the pivot to enhance instruction tuning in lower-resource languages. It trains the model to first process instructions in the pivot language, and then produce responses in the target language. To evaluate our approach, we introduce a benchmark, X-AlpacaEval, of instructions in 4 languages (Chinese, Korean, Italian, and Spanish), each annotated by professional translators. Our approach demonstrates a significant improvement in the instruction-following abilities of LLMs by 29% on average, compared to directly responding in the target language alone. Further experiments validate the versatility of our approach by employing alternative pivot languages beyond English to assist languages where LLMs exhibit lower proficiency. Our code and data are available at https://github.com/ytyz1307zzh/PLUG.

The success of online social platforms hinges on their ability to predict and understand user behavior at scale. Here, we present data suggesting that context-aware modeling approaches may offer a holistic yet lightweight and potentially privacy-preserving representation of user engagement on online social platforms. Leveraging deep LSTM neural networks to analyze more than 100 million Snapchat sessions from almost 80.000 users, we demonstrate that patterns of active and passive use are predictable from past behavior (R2=0.345) and that the integration of context information substantially improves predictive performance compared to the behavioral baseline model (R2=0.522). Features related to smartphone connectivity status, location, temporal context, and weather were found to capture non-redundant variance in user engagement relative to features derived from histories of in-app behaviors. Further, we show that a large proportion of variance can be accounted for with minimal behavioral histories if momentary context information is considered (R2=0.44). These results indicate the potential of context-aware approaches for making models more efficient and privacy-preserving by reducing the need for long data histories. Finally, we employ model explainability techniques to glean preliminary insights into the underlying behavioral mechanisms. Our findings are consistent with the notion of context-contingent, habit-driven patterns of active and passive use, underscoring the value of contextualized representations of user behavior for predicting user engagement on social platforms.

Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging., Comment: EMNLP 2023 Findings

This paper introduces a large collection of time series data derived from Twitter, postprocessed using word embedding techniques, as well as specialized fine-tuned language models. This data comprises the past five years and captures changes in n-gram frequency, similarity, sentiment and topic distribution. The interface built on top of this data enables temporal analysis for detecting and characterizing shifts in meaning, including complementary information to trending metrics, such as sentiment and topic association over time. We release an online demo for easy experimentation, and we share code and the underlying aggregated data for future work. In this paper, we also discuss three case studies unlocked thanks to our platform, showcasing its potential for temporal linguistic analysis., Comment: Demo paper. Visualization platform available at https://tweetnlp.org/insights

Geothermal soils in Central Italy are characterized by high temperatures (up to 60°C), low pH values, and sparse vegetation. The biodiversity of entomopathogenic soil fungi and nematodes has never been assessed in these areas. Soil samples (N = 12) separated from each other by at least 100 meters were collected in the areas of Le Biancane Natural Park (Grosseto) and Sasso Pisano (Pisa). The Galleria bait method was used to assess the presence of entomopathogenic fungi and nematodes. A total of nine species of fungi and one nematode were isolated and molecularly identified. All these species came from samples collected in the immediate surroundings of geothermal spring, apart from one Beauveria pseudobassiana collected at about 16 meters from the nearest spring. Moreover, Pristionchus uniformis previously reported only from North America and few European countries is recorded for the first time in Italy.&nbsp

Geothermal soils in Central Italy are characterized by high temperatures (up to 60°C), low pH values, and sparse vegetation. The biodiversity of entomopathogenic soil fungi and nematodes has never been assessed in these areas. Soil samples (N = 12) separated from each other by at least 100 meters were collected in the areas of Le Biancane Natural Park (Grosseto) and Sasso Pisano (Pisa). The Galleria bait method was used to assess the presence of entomopathogenic fungi and nematodes. A total of nine species of fungi and one nematode were isolated and molecularly identified. All these species came from samples collected in the immediate surroundings of geothermal spring, apart from one Beauveria pseudobassiana collected at about 16 meters from the nearest spring. Moreover, Pristionchus uniformis previously reported only from North America and few European countries is recorded for the first time in Italy.&nbsp

Pictorial emojis and stickers are commonly used in online social networking to facilitate and aid communications. We delve into the use of Bitmoji stickers, a highly expressive form of pictorial communication using avatars resembling actual users. We collect a large-scale dataset of the metadata of 3 billion Bitmoji stickers shared among 300 million Snapchat users. We find that individual Bitmoji sticker usage patterns can be characterized jointly on dimensions of reciprocity and selectivity: Users are either both reciprocal and selective about whom they use Bitmoji stickers with or neither reciprocal nor selective. We additionally provide evidence of network homophily in that friends use Bitmoji stickers at similar rates. Finally, using a quasi-experimental approach, we show that receiving Bitmoji stickers from a friend encourages future Bitmoji sticker usage and overall Snapchat engagement. We discuss broader implications of our work towards a better understanding of pictorial communication behaviors in social networks., Comment: 14 pages, 10 figures, 4 tables

Recent progress in language model pre-training has led to important improvements in Named Entity Recognition (NER). Nonetheless, this progress has been mainly tested in well-formatted documents such as news, Wikipedia, or scientific articles. In social media the landscape is different, in which it adds another layer of complexity due to its noisy and dynamic nature. In this paper, we focus on NER in Twitter, one of the largest social media platforms, and construct a new NER dataset, TweetNER7, which contains seven entity types annotated over 11,382 tweets from September 2019 to August 2021. The dataset was constructed by carefully distributing the tweets over time and taking representative trends as a basis. Along with the dataset, we provide a set of language model baselines and perform an analysis on the language model performance on the task, especially analyzing the impact of different time periods. In particular, we focus on three important temporal aspects in our analysis: short-term degradation of NER models over time, strategies to fine-tune a language model over different periods, and self-labeling as an alternative to lack of recently-labeled data. TweetNER7 is released publicly (https://huggingface.co/datasets/tner/tweetner7) along with the models fine-tuned on it., Comment: AACL 2022 main conference

We propose MINT, a new Multilingual INTimacy analysis dataset covering 13,372 tweets in 10 languages including English, French, Spanish, Italian, Portuguese, Korean, Dutch, Chinese, Hindi, and Arabic. We benchmarked a list of popular multilingual pre-trained language models. The dataset is released along with the SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis (https://sites.google.com/umich.edu/semeval-2023-tweet-intimacy)., Comment: SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis

Social media platforms host discussions about a wide variety of topics that arise everyday. Making sense of all the content and organising it into categories is an arduous task. A common way to deal with this issue is relying on topic modeling, but topics discovered using this technique are difficult to interpret and can differ from corpus to corpus. In this paper, we present a new task based on tweet topic classification and release two associated datasets. Given a wide range of topics covering the most important discussion points in social media, we provide training and testing data from recent time periods that can be used to evaluate tweet classification models. Moreover, we perform a quantitative evaluation and analysis of current general- and domain-specific language models on the task, which provide more insights on the challenges and nature of the task., Comment: Accepted at COLING 2022

Language evolves over time, and word meaning changes accordingly. This is especially true in social media, since its dynamic nature leads to faster semantic shifts, making it challenging for NLP models to deal with new content and trends. However, the number of datasets and models that specifically address the dynamic nature of these social platforms is scarce. To bridge this gap, we present TempoWiC, a new benchmark especially aimed at accelerating research in social media-based meaning shift. Our results show that TempoWiC is a challenging benchmark, even for recently-released language models specialized in social media., Comment: Accepted to COLING 2022. Used to create the TempoWiC Shared Task for EvoNLP

The increasing prevalence of location-sharing features on social media has enabled researchers to ground computational social science research using geolocated data, affording opportunities to study human mobility, the impact of real-world events, and more. This paper analyzes what crucially separates posts with geotags from those without. We find that users who share location are not representative of the social media user population at large, jeopardizing the generalizability of research that uses only geolocated data.We consider three aspects: affect -- sentiment and emotions, content -- textual and non-textual, and audience engagement. By comparing a dataset of 1.3 million geotagged tweets with a random dataset of the same size, we show that geotagged posts on Twitter exhibit significantly more positivity, are often about joyous and special events such as weddings or graduations, convey more collectivism rather than individualism, and contain more additional features such as hashtags or objects in images, but at the same time generate substantially less engagement. These findings suggest there exist significant differences in the messages conveyed in geotagged posts. Our research carries important implications for future research utilizing geolocation social media data., Comment: 11 pages, 10 figures, 2 tables

In this paper we present TweetNLP, an integrated platform for Natural Language Processing (NLP) in social media. TweetNLP supports a diverse set of NLP tasks, including generic focus areas such as sentiment analysis and named entity recognition, as well as social media-specific tasks such as emoji prediction and offensive language identification. Task-specific systems are powered by reasonably-sized Transformer-based language models specialized on social media text (in particular, Twitter) which can be run without the need for dedicated hardware or cloud services. The main contributions of TweetNLP are: (1) an integrated Python library for a modern toolkit supporting social media analysis using our various task-specific models adapted to the social domain; (2) an interactive online demo for codeless experimentation using our models; and (3) a tutorial covering a wide variety of typical social media applications., Comment: EMNLP 2022 Demo paper. TweetNLP: https://tweetnlp.org

Most methods for conditional video synthesis use a single modality as the condition. This comes with major limitations. For example, it is problematic for a model conditioned on an image to generate a specific motion trajectory desired by the user since there is no means to provide motion information. Conversely, language information can describe the desired motion, while not precisely defining the content of the video. This work presents a multimodal video generation framework that benefits from text and images provided jointly or separately. We leverage the recent progress in quantized representations for videos and apply a bidirectional transformer with multiple modalities as inputs to predict a discrete video representation. To improve video quality and consistency, we propose a new video token trained with self-learning and an improved mask-prediction algorithm for sampling video tokens. We introduce text augmentation to improve the robustness of the textual representation and diversity of generated videos. Our framework can incorporate various visual modalities, such as segmentation masks, drawings, and partially occluded images. It can generate much longer sequences than the one used for training. In addition, our model can extract visual information as suggested by the text prompt, e.g., "an object in image one is moving northeast", and generate corresponding videos. We run evaluations on three public datasets and a newly collected dataset labeled with facial attributes, achieving state-of-the-art generation results on all four., Comment: Accepted to CVPR 2022

Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models' capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift., Comment: Accepted to ACL 2022 (Demo Track) - https://github.com/cardiffnlp/timelms

Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty languages, alongside starter code to subsequently fine-tune on a target task; and (2) a set of unified sentiment analysis Twitter datasets in eight different languages and a XLM-T model fine-tuned on them., Comment: LREC 2022. Code and data available at https://github.com/cardiffnlp/xlm-t

Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity in recent years. Extensive work shows how accurately such models can represent abstract, semantic information present in text. In this expository work, we explore a tangent direction and analyze such models' performance on tasks that require a more granular level of representation. We focus on the problem of textual similarity from two perspectives: matching documents on a granular level (requiring embeddings to capture fine-grained attributes in the text), and an abstract level (requiring embeddings to capture overall textual semantics). We empirically demonstrate, across two datasets from different domains, that despite high performance in abstract document matching as expected, contextual embeddings are consistently (and at times, vastly) outperformed by simple baselines like TF-IDF for more granular tasks. We then propose a simple but effective method to incorporate TF-IDF into models that use contextual embeddings, achieving relative improvements of up to 36% on granular tasks., Comment: Accepted at COLING 2020. Code available at https://github.com/brihijoshi/granular-similarity-COLING-2020

The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction. Therefore, it is unclear what the current state of the art is, as there is no standardized evaluation protocol, neither a strong set of baselines trained on such domain-specific data. In this paper, we propose a new evaluation framework (TweetEval) consisting of seven heterogeneous Twitter-specific classification tasks. We also provide a strong set of baselines as starting point, and compare different language modeling pre-training strategies. Our initial experiments show the effectiveness of starting off with existing pre-trained generic language models, and continue training them on Twitter corpora., Comment: Findings of EMNLP 2020. TweetEval benchmark available at https://github.com/cardiffnlp/tweeteval

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data representations, and using auxiliary training objectives to mitigate bias during fine-tuning. Although these techniques achieve bias reduction for the task and domain at hand, the effects of bias mitigation may not directly transfer to new tasks, requiring additional data collection and customized annotation of sensitive attributes, and re-evaluation of appropriate fairness metrics. We explore the feasibility and benefits of upstream bias mitigation (UBM) for reducing bias on downstream tasks, by first applying bias mitigation to an upstream model through fine-tuning and subsequently using it for downstream fine-tuning. We find, in extensive experiments across hate speech detection, toxicity detection, occupation prediction, and coreference resolution tasks over various bias factors, that the effects of UBM are indeed transferable to new downstream tasks or domains via fine-tuning, creating less biased downstream models than directly fine-tuning on the downstream task or transferring from a vanilla upstream model. Though challenges remain, we show that UBM promises more efficient and accessible bias mitigation in LM fine-tuning., Comment: 14 pages; Accepted at NAACL 2021

Cross-lingual embeddings represent the meaning of words from different languages in the same vector space. Recent work has shown that it is possible to construct such representations by aligning independently learned monolingual embedding spaces, and that accurate alignments can be obtained even without external bilingual data. In this paper we explore a research direction that has been surprisingly neglected in the literature: leveraging noisy user-generated text to learn cross-lingual embeddings particularly tailored towards social media applications. While the noisiness and informal nature of the social media genre poses additional challenges to cross-lingual embedding methods, we find that it also provides key opportunities due to the abundance of code-switching and the existence of a shared vocabulary of emoji and named entities. Our contribution consists of a very simple post-processing step that exploits these phenomena to significantly improve the performance of state-of-the-art alignment methods., Comment: Accepted to ICWSM 2020. 11 pages, 1 appendix. Pre-trained embeddings available at https://github.com/pedrada88/crossembeddings-twitter

The frequent use of Emojis on social media platforms has created a new form of multimodal social interaction. Developing methods for the study and representation of emoji semantics helps to improve future multimodal communication systems. In this paper, we explore the usage and semantics of emojis over time. We compare emoji embeddings trained on a corpus of different seasons and show that some emojis are used differently depending on the time of the year. Moreover, we propose a method to take into account the time information for emoji prediction systems, outperforming state-of-the-art systems. We show that, using the time information, the accuracy of some emojis can be significantly improved., Comment: Emojis @ ICWSM 2018

Emojis are small images that are commonly included in social media text messages. The combination of visual and textual content in the same message builds up a modern way of communication, that automatic systems are not used to deal with. In this paper we extend recent advances in emoji prediction by putting forward a multimodal approach that is able to predict emojis in Instagram posts. Instagram posts are composed of pictures together with texts which sometimes include emojis. We show that these emojis can be predicted by using the text, but also using the picture. Our main finding is that incorporating the two synergistic modalities, in a combined model, improves accuracy in an emoji prediction task. This result demonstrates that these two modalities (text and images) encode different information on the use of emojis and therefore can complement each other., Comment: NAACL 2018 (short)

Music genres allow to categorize musical items that share common characteristics. Although these categories are not mutually exclusive, most related research is traditionally focused on classifying tracks into a single class. Furthermore, these categories (e.g., Pop, Rock) tend to be too broad for certain applications. In this work we aim to expand this task by categorizing musical items into multiple and fine-grained labels, using three different data modalities: audio, text, and images. To this end we present MuMu, a new dataset of more than 31k albums classified into 250 genre classes. For every album we have collected the cover image, text reviews, and audio tracks. Additionally, we propose an approach for multi-label genre classification based on the combination of feature embeddings learned with state-of-the-art deep learning methodologies. Experiments show major differences between modalities, which not only introduce new baselines for multi-label genre classification, but also suggest that combining them yields improved results., Comment: In Proceedings of the 18th International Society of Music Information Retrieval Conference (ISMIR 2017)

Emojis are ideograms which are naturally combined with plain text to visually complement or condense the meaning of a message. Despite being widely used in social media, their underlying semantics have received little attention from a Natural Language Processing standpoint. In this paper, we investigate the relation between words and emojis, studying the novel task of predicting which emojis are evoked by text-based tweet messages. We train several models based on Long Short-Term Memory networks (LSTMs) in this task. Our experimental results show that our neural model outperforms two baselines as well as humans solving the same task, suggesting that computational models are able to better capture the underlying semantics of emojis., Comment: To appear at EACL 2017

Computational approaches to analyze figurative language are attracting a growing interest in Computational Linguistics. In this paper, we study the characterization of Twitter messages in Spanish that advertise satirical news. We present and evaluate a system able to classify tweets as satirical or not. To this purpose, we concentrate on the tweets published by several satirical and non-satirical Twitter accounts. We model the text of each tweet by a set of linguistically motivated features that aim at capturing the style more than the content of the message. Our experiments demonstrate that our model outperforms a word-based baseline. We also demonstrate that our system models global features of satirical language by showing that it is able to detect if a tweet contains or not satirical contents independently from the account that generated the tweet., La lingüística computacional está cada vez más interesada en el procesamiento del lenguaje figurado. En este artículo estudiamos la detección de noticias satíricas en español y más específicamente la detección de sátira en mensajes de Twitter. Nuestro modelo computacional se basa en la representación de cada mensaje con un conjunto de rasgos diseñados para detectar el estilo satírico y no el contenido. Nuestros experimentos muestran que nuestro modelo siempre funciona mejor que un modelo de bolsa de palabras. También mostramos que el sistema es capaz de detectar este tipo de lenguaje independientemente de la cuenta de Twitter que lo origina.

In this article we present a Web-based demonstration of on-line text summarization and information extraction technology. News summarization in Spanish has been implemented in a system that monitors a news provider and summarizes the latest published news. The possibility to generate summaries from user's provided text is also available for English and Spanish. The demonstrator also features event extraction functionalities since it identifies the relevant concepts that characterize several types of events by mining English textual contents., En este artículo describimos la demonstración de una serie de aplicaciones de resumen automático y extracción de informaciones integradas en una tableta. Se presentan funcionalidades para resumir las últimas noticias publicadas en la Web, extraer información sobre eventos concretos, y resumir textos en inglés y español ingresados por el usuario. La aplicación está disponible en un Web-browser y una tableta con sistema operativo Android.

In this article we present a Web-based demonstration of on-line text summarization and information extraction technology. News summarization in Spanish has been implemented in a system that monitors a news provider and summarizes the latest published news. The possibility to generate summaries from user's provided text is also available for English and Spanish. The demonstrator also features event extraction functionalities since it identifies the relevant concepts that characterize several types of events by mining English textual contents., En este artículo describimos la demonstración de una serie de aplicaciones de resumen automático y extracción de informaciones integradas en una tableta. Se presentan funcionalidades para resumir las últimas noticias publicadas en la Web, extraer información sobre eventos concretos, y resumir textos en inglés y español ingresados por el usuario. La aplicación está disponible en un Web-browser y una tableta con sistema operativo Android.

Computational approaches to analyze figurative language are attracting a growing interest in Computational Linguistics. In this paper, we study the characterization of Twitter messages in Spanish that advertise satirical news. We present and evaluate a system able to classify tweets as satirical or not. To this purpose, we concentrate on the tweets published by several satirical and non-satirical Twitter accounts. We model the text of each tweet by a set of linguistically motivated features that aim at capturing the style more than the content of the message. Our experiments demonstrate that our model outperforms a word-based baseline. We also demonstrate that our system models global features of satirical language by showing that it is able to detect if a tweet contains or not satirical contents independently from the account that generated the tweet., La lingüística computacional está cada vez más interesada en el procesamiento del lenguaje figurado. En este artículo estudiamos la detección de noticias satíricas en español y más específicamente la detección de sátira en mensajes de Twitter. Nuestro modelo computacional se basa en la representación de cada mensaje con un conjunto de rasgos diseñados para detectar el estilo satírico y no el contenido. Nuestros experimentos muestran que nuestro modelo siempre funciona mejor que un modelo de bolsa de palabras. También mostramos que el sistema es capaz de detectar este tipo de lenguaje independientemente de la cuenta de Twitter que lo origina.

Scopo del lavoro è quello di tracciare un parallelismo tra la narrativa giapponese e angloamericana contemporanea, viste come parte di un sistema di significati che trascende la dimensione nazionale e si installa invece in una dinamica di tipo globale. Le opere letterarie prese in considerazione sono alcune fra quelle ambientate nelle due vere e proprie capitali culturali dei paesi, rispettivamente New York per gli Stati Uniti e Tōkyō per il Giappone. Spunto di partenza dell’analisi è stato il concetto di “global city”, formulato dalla studiosa e sociologa Saskia Sassen, che permette di mettere in relazione dal punto di vista economico, strutturale ma anche sociale le città di New York e Tōkyō. Tale formulazione consente infatti di ragionare in maniera motivata sull’esistenza di un rapporto di flussi di scambio di tipo culturale e, parallelamente, sull’acquisizione di una dimensione di tipo transnazionale di soggetti e tematiche della letteratura. In questo senso, il rapporto tra economia e globalizzazione evidenziato da Sassen può essere paragonato a quello che intercorre tra la letteratura e la globalizzazione. Punto di snodo metodologico del lavoro è rappresentato dall’analisi dello spazio urbano, esaminato sia in chiave urbanistico-architettonica che più specificamente letteraria., The research aims at drawing a parallelism between contemporary American and Japanese fiction. Moving from the definition provided by Saskia Sassen of “global city”, the analysis concentrates on the representation of urban space in a selection of novels set in New York and Tōkyō, to underline similarities in subject and themes of contemporary literary expression that are valid in a transnational dimension.

Scopo del lavoro è quello di tracciare un parallelismo tra la narrativa giapponese e angloamericana contemporanea, viste come parte di un sistema di significati che trascende la dimensione nazionale e si installa invece in una dinamica di tipo globale. Le opere letterarie prese in considerazione sono alcune fra quelle ambientate nelle due vere e proprie capitali culturali dei paesi, rispettivamente New York per gli Stati Uniti e Tōkyō per il Giappone. Spunto di partenza dell’analisi è stato il concetto di “global city”, formulato dalla studiosa e sociologa Saskia Sassen, che permette di mettere in relazione dal punto di vista economico, strutturale ma anche sociale le città di New York e Tōkyō. Tale formulazione consente infatti di ragionare in maniera motivata sull’esistenza di un rapporto di flussi di scambio di tipo culturale e, parallelamente, sull’acquisizione di una dimensione di tipo transnazionale di soggetti e tematiche della letteratura. In questo senso, il rapporto tra economia e globalizzazione evidenziato da Sassen può essere paragonato a quello che intercorre tra la letteratura e la globalizzazione. Punto di snodo metodologico del lavoro è rappresentato dall’analisi dello spazio urbano, esaminato sia in chiave urbanistico-architettonica che più specificamente letteraria., The research aims at drawing a parallelism between contemporary American and Japanese fiction. Moving from the definition provided by Saskia Sassen of “global city”, the analysis concentrates on the representation of urban space in a selection of novels set in New York and Tōkyō, to underline similarities in subject and themes of contemporary literary expression that are valid in a transnational dimension.

A new genus is proposed within the family Geophilidae: Hyphydrophilus n. gen., for H. adisi n.sp. Four additional new species are described, i.e. the ballophilids ltyphilus crabilli n.sp. and Taeniolinllm arborum n.sp. and the schendylids Pecfiniunguis ascendens n.sp. and Schendyluflls amazonicl/s n.sp. The geophilid species Ribautia centralis (SILVESTRI, 1907) is redescribed, after material from Brazil compared with the holotype. The ballophilid Thalthybil/s perrieri BROLEMANN, 1909 is transferred to the genus ltyphi/us COOK, 1889 and a lectotype is designated here for it., É sugerido um novo gênero para H. adisi n.sp. na família Oeophilidae: Hyphydrophilus n. gen. Quatro espécies adicionais são descritas: os ballophilideos Ityphi/lIs crabil/i n.sp. e Taeniolinllm arbomm n.sp. e os schendylideos Pectiniunguis ascendens n.sp. e Schendylurlls amazoniclIs n.sp. O geophilideo Ribautia centralis (SILVESTRI, 1907) é redescrito, baseado em material do Brasil comparado com o holotipo. O ballophilideo Thalthybius perrieri BRÓLEMANN, 1909 é transferido para o gênero ltyphillls COOK, 1889, sendo designado Icctotipo.

Le attività sviluppate nel presente lavoro di tesi rientrano nelle tematiche dalla moderna Bioeconomia e seguono le direttive previste per l’applicazione dell’economia circolare applicata all'insieme dei rifiuti legnosi prodotti dalla potatura, sfalci del sottobosco e dai rifiuti legnosi di tipo urbano (post consumo, ingombranti, fine vita, ecc.). Viene studiatala valorizzazione delle frazioni dei rifiuti lignocellulosici studiando processi alternativi a quelli usati sino ad oggi verificando se da tali matrici fosse possibile attraverso processi di idrolisi biologica, termica o chimica ottenere carboidrati semplici con il fine di ottenere molecole di interesse per la chimica fine. L’obiettivo rientra nella valorizzazione della frazione carboniosa presente in tali matrici, in alternativa all'uso di fonti di origine minerale (petrolio e carbone). Le attività studiate hanno preso in considerazione l’uso dei pretrattamenti necessari (Triturazione, Water Vapor Steam Expolsion) e lo studio di diversi processi di idrolisi (enzimatica con uso di funghi, idrolisi termica e chimica in condizioni idrotermali), al fine di verificare e quantificare le molecole presenti nelle matrici idrolizzate rispetto alla tipologia di rifiuto legnoso considerato. Dal confronto dei liquidi ottenuti, tramite GC-MS, risulta che è possibile ottenere una maggior quantità di zuccheri semplici dai rifiuti legnosi (freschi) rispetto al legno da rifiuto antropico (post consumo). Dai risultati emerge che i processi di idrolisi in condizioni idrotermali a pH acido e basico ottengono elevate rese di degradazione delle matrici legnose rispetto a quelle ottenute con i processi enzimatici. La valorizzazione delle molecole degradate ottenute con i processi di idrolisi sarà necessaria ai fini di permettere l’individuazione dell’insieme dei processi necessari per la chiusura del ciclo e, in base al tipo di prodotti ottenibili, eseguire una corretta valutazione economica di tutto il processo integrato.

Si studia in modo formale una specifica proprietà della Computazione Quantistica. In particolare, il modello di calcolo che si utilizzerà (circuito quantistico) può essere rappresentato da una sequenza di operazioni. Una sequenza è detta mista (circuito misto) se si presentano operazioni classiche e quantistiche in modo alternato (sequenze del tipo Q-C-C-Q-Q-C). Una sequenza in Forma Normale, invece, ammette operazioni classiche solamente all'inizio o alla fine, mentre in mezzo possono esserci solamente operazioni quantistiche (sequenze del tipo C-C-Q-Q-Q-C). Una sequenza di operazioni esclusivamente quantistiche porta numerosi vantaggi, per questo la forma normale è molto importante. Essa infatti separa le operazioni classiche da quelle quantistiche, concentrandole tutte all'interno. Quello che si farà in questa tesi sarà fornire un modo operativo (mediante riscritture) per ottenere la forma normale di una qualsiasi sequenza di operazioni classiche o quantistiche.

Le attività sviluppate nel presente lavoro di tesi rientrano nelle tematiche dalla moderna Bioeconomia e seguono le direttive previste per l’applicazione dell’economia circolare applicata all'insieme dei rifiuti legnosi prodotti dalla potatura, sfalci del sottobosco e dai rifiuti legnosi di tipo urbano (post consumo, ingombranti, fine vita, ecc.). Viene studiatala valorizzazione delle frazioni dei rifiuti lignocellulosici studiando processi alternativi a quelli usati sino ad oggi verificando se da tali matrici fosse possibile attraverso processi di idrolisi biologica, termica o chimica ottenere carboidrati semplici con il fine di ottenere molecole di interesse per la chimica fine. L’obiettivo rientra nella valorizzazione della frazione carboniosa presente in tali matrici, in alternativa all'uso di fonti di origine minerale (petrolio e carbone). Le attività studiate hanno preso in considerazione l’uso dei pretrattamenti necessari (Triturazione, Water Vapor Steam Expolsion) e lo studio di diversi processi di idrolisi (enzimatica con uso di funghi, idrolisi termica e chimica in condizioni idrotermali), al fine di verificare e quantificare le molecole presenti nelle matrici idrolizzate rispetto alla tipologia di rifiuto legnoso considerato. Dal confronto dei liquidi ottenuti, tramite GC-MS, risulta che è possibile ottenere una maggior quantità di zuccheri semplici dai rifiuti legnosi (freschi) rispetto al legno da rifiuto antropico (post consumo). Dai risultati emerge che i processi di idrolisi in condizioni idrotermali a pH acido e basico ottengono elevate rese di degradazione delle matrici legnose rispetto a quelle ottenute con i processi enzimatici. La valorizzazione delle molecole degradate ottenute con i processi di idrolisi sarà necessaria ai fini di permettere l’individuazione dell’insieme dei processi necessari per la chiusura del ciclo e, in base al tipo di prodotti ottenibili, eseguire una corretta valutazione economica di tutto il processo integrato.

Si studia in modo formale una specifica proprietà della Computazione Quantistica. In particolare, il modello di calcolo che si utilizzerà (circuito quantistico) può essere rappresentato da una sequenza di operazioni. Una sequenza è detta mista (circuito misto) se si presentano operazioni classiche e quantistiche in modo alternato (sequenze del tipo Q-C-C-Q-Q-C). Una sequenza in Forma Normale, invece, ammette operazioni classiche solamente all'inizio o alla fine, mentre in mezzo possono esserci solamente operazioni quantistiche (sequenze del tipo C-C-Q-Q-Q-C). Una sequenza di operazioni esclusivamente quantistiche porta numerosi vantaggi, per questo la forma normale è molto importante. Essa infatti separa le operazioni classiche da quelle quantistiche, concentrandole tutte all'interno. Quello che si farà in questa tesi sarà fornire un modo operativo (mediante riscritture) per ottenere la forma normale di una qualsiasi sequenza di operazioni classiche o quantistiche.

This paper describes the results of the first shared task on Multilingual Emoji Prediction, organized as part of SemEval 2018. Given the text of a tweet, the task consists of predicting the most likely emoji to be used along such tweet. Two subtasks were proposed, one for English and one for Spanish, and participants were allowed to submit a system run to one or both subtasks. In total, 49 teams participated in the English subtask and 22 teams submitted a system run to the Spanish subtask. Evaluation was carried out emoji-wise, and the final ranking was based on macro F-Score. Data and further information about this task can be found at https://competitions. codalab.org/competitions/17344.

In this paper we analyze the use of emojis in social media with respect to gender and skin tone. By gathering a dataset of over twenty two million tweets from United States some findings are clearly highlighted after performing a simple frequency-based analysis. Moreover, we carry out a semantic analysis on the usage of emojis and their modifiers (e.g. gender and skin tone) by embedding all words, emojis and modifiers into the same vector space. Our analyses reveal that some stereotypes related to the skin color and gender seem to be reflected on the use of these modifiers. For example, emojis representing hand gestures are more widely utilized with lighter skin tones, and the usage across skin tones differs significantly. At the same time, the vector corresponding to the male modifier tends to be semantically close to emojis related to business or technology, whereas their female counterparts appear closer to emojis about love or makeup.

Human language has evolved towards newer forms of communication such as social media, where emojis (i.e., ideograms bearing a visual meaning) play a key role. While there is an increasing body of work aimed at the computational modeling of emoji semantics, there is currently little understanding about what makes a computational model represent or predict a given emoji in a certain way. In this paper we propose a label-wise attention mechanism with which we attempt to better understand the nuances underlying emoji prediction. In addition to advantages in terms of interpretability, we show that our proposed architecture improves over standard baselines in emoji prediction, and does particularly well when predicting infrequent emojis.

Human language has evolved towards newer forms of communication such as social media, where emojis (i.e., ideograms bearing a visual meaning) play a key role. While there is an increasing body of work aimed at the computational modeling of emoji semantics, there is currently little understanding about what makes a computational model represent or predict a given emoji in a certain way. In this paper we propose a label-wise attention mechanism with which we attempt to better understand the nuances underlying emoji prediction. In addition to advantages in terms of interpretability, we show that our proposed architecture improves over standard baselines in emoji prediction, and does particularly well when predicting infrequent emojis.