Search

Document similarity recognition is one of the most important problems in natural language processing. This paper proposes a plagiarism comparison mechanism called JCF. Initially, the TF–IDF scheme is applied to build a bag of words as the representation of the common features of all documents. Then, the plagiarism comparison is carried out in a coarse-grained manner, which speeds up the similarity comparison. Finally, the most similar documents can then be compared in detail based on a fine-grained approach. In addition, the JCF detects plagiarism at both syntax level and semantic-like level. To prevent the distortion of similarity comparison, this paper further develops a similarity restoration approach such that the proposed JCF can obtain both advantages of quickness and accuracy. Performance studies confirm that the proposed JCF outperforms existing studies in terms of precision, recall and F1 score. [ABSTRACT FROM AUTHOR]

Microelectronics production failure analysis is an important step in improving product quality and development. In fact, the understanding of the failure mechanisms and therefore the implementation of corrective actions on the cause of the failure depend on the results of this analysis. These analyses are saved under textual features format. Then such data need first to be preprocessed and vectorized (converted to numeric). Second, to overcome the curse of dimensionality caused by the vectorisation process, a dimension reduction is applied. A two-stage variable selection and feature extraction is used to reduce the high dimensionality of a feature space. We are first interested in studying the potential of using an unsupervised variable selection technique, the genetic algorithm, to identify the variables that best demonstrate discrimination in the separation and compactness of groups of textual data. The genetic algorithm uses a combination of the K-means or Gaussian Mixture Model clustering and validity indices as a fitness function for optimization. Such a function improves both compactness and class separation. The second work looks into the feasibility of applying a feature extraction technique. The adopted methodology is a Deep learning algorithm based on variational autoencoder (VAE) for latent space disentanglement and Gaussian Mixture Model for clustering of the latent space for cluster identification. The last objective of this paper is to propose a new methodology based on the combination between variational autoencoder (VAE) for the latent space disentanglement, and genetic algorithm (GA) to find, in an unsupervised way, the latent variables allowing the best discrimination of clusters of failure analysis data. This methodology is called VAE-GA. Experiments on textual datasets of failure analysis demonstrate the effectiveness of the VAE-GA proposed method which allows better discrimination of textual classes compared to the use of GA or VAE separately or the combination of PCA with GA (PCA-GA) or a simple Auto-encoders with GA (AE-GA). [ABSTRACT FROM AUTHOR]

Business process compliance is an essential part of business process management, which saves organizations from penalties caused by non-compliant processes. However, current researches on business process compliance mainly focus on checking using general constraint rules that have been formalized without in-depth analysis of related regulatory documents and mostly involve extensive human efforts. In this paper, we aim to propose an automatic and interpretable compliance checking approach for design-time business processes. By combining deep learning and a natural language processing approach based on rule templates, we extract semantic information from regulatory documents at different granularities for subsequent compliance checking. In addition, we match appropriate rules to the process model and detect the degree of violation of the business process from three control-flow perspectives. The effectiveness of this method is validated on two real-world datasets. [ABSTRACT FROM AUTHOR]

Semantic relatedness is one of the most significant aspects of natural language processing. It has been identified as a critical technology for developing intelligent systems like Siri, Microsoft Ice, Cortana, and Xiaoai. In 2014, SemEval ranked SR as the top task. While many existing studies have focused on analyzing the entailment of single phrases, advancements in deep learning have made it possible to analyze complete sentences or texts. While the natural parallelism of membrane computing has shown promise for data processing, harnessing this potential to advance semantic relatedness remains an open problem yet to be tackled. This paper proposes a novel Siamese Manhattan LSTM-SNP approach (SiMaLSTM-SNP) for the SR problem. The approach uses a collaborative Word2vec and 10-Layer Attention strategy to represent and extract sentence pairs and a Siamese LSTM-SNP structure to calculate the hidden states of sentences. The multi-head self-attention layer identifies text associations and redistributes hidden state weights. The last hidden state is extracted, and the relatedness score is calculated using the Manhattan distance. The experiments demonstrate that SiMaLSTM-SNP outperforms 17 classical SR baselines and 7 novel approaches on the standard datasets SICK and STS in terms of mean square error performance. This indicates that SiMaLSTM-SNP can accurately capture the semantic distinction between two sentences and effectively preserve their semantic information. [ABSTRACT FROM AUTHOR]

Span-level method achieves competitive results in Aspect Sentiment Triplet Extraction (ASTE) by enumerating all possible spans. However, previous span-level methods fail to exploit syntactic information to identify the correspondence between aspect terms and opinion terms, which makes the extracted triplets inaccurate. In this paper, we propose a syntactic and semantic dual-enhanced bidirectional network (SSBN) for ASTE task. By constructing word dependencies as a graph and embedding them into features to capture syntactic information more effectively in bidirectional network. Furthermore, we design a pruning strategy that uses part-of-speech information to alleviate the problem of identifying potential aspects and opinions from a large number of spans. We conduct extensive experiments on four benchmark datasets, and the experimental results demonstrate the effectiveness of the SSBN model. [ABSTRACT FROM AUTHOR]

Since the spread of the coronavirus flu in 2019 (hereafter referred to as COVID-19), millions of people worldwide have been affected by the pandemic, which has significantly impacted our habits in various ways. In order to eradicate the disease, a great help came from unprecedentedly fast vaccines development along with strict preventive measures adoption like lockdown. Thus, world wide provisioning of vaccines was crucial in order to achieve the maximum immunization of population. However, the fast development of vaccines, driven by the urge of limiting the pandemic caused skeptical reactions by a vast amount of population. More specifically, the people's hesitancy in getting vaccinated was an additional obstacle in fighting COVID-19. To ameliorate this scenario, it is important to understand people's sentiments about vaccines in order to take proper actions to better inform the population. As a matter of fact, people continuously update their feelings and sentiments on social media, thus a proper analysis of those opinions is an important challenge for providing proper information to avoid misinformation. More in detail, sentiment analysis (Wankhade et al. in Artif Intell Rev 55(7):5731–5780, 2022. https://doi.org/10.1007/s10462-022-10144-1) is a powerful technique in natural language processing that enables the identification and classification of people feelings (mainly) in text data. It involves the use of machine learning algorithms and other computational techniques to analyze large volumes of text and determine whether they express positive, negative or neutral sentiment. Sentiment analysis is widely used in industries such as marketing, customer service, and healthcare, among others, to gain actionable insights from customer feedback, social media posts, and other forms of unstructured textual data. In this paper, Sentiment Analysis will be used to elaborate on people reaction to COVID-19 vaccines in order to provide useful insights to improve the correct understanding of their correct usage and possible advantages. In this paper, a framework that leverages artificial intelligence (AI) methods is proposed for classifying tweets based on their polarity values. We analyzed Twitter data related to COVID-19 vaccines after the most appropriate pre-processing on them. More specifically, we identified the word-cloud of negative, positive, and neutral words using an artificial intelligence tool to determine the sentiment of tweets. After this pre-processing step, we performed classification using the BERT + NBSVM model to classify people's sentiments about vaccines. The reason for choosing to combine bidirectional encoder representations from transformers (BERT) and Naive Bayes and support vector machine (NBSVM) can be understood by considering the limitation of BERT-based approaches, which only leverage encoder layers, resulting in lower performance on short texts like the ones used in our analysis. Such a limitation can be ameliorated by using Naive Bayes and Support Vector Machine approaches that are able to achieve higher performance in short text sentiment analysis. Thus, we took advantage of both BERT features and NBSVM features to define a flexible framework for our sentiment analysis goal related to vaccine sentiment identification. Moreover, we enrich our results with spatial analysis of the data by using geo-coding, visualization, and spatial correlation analysis to suggest the most suitable vaccination centers to users based on the sentiment analysis outcomes. In principle, we do not need to implement a distributed architecture to run our experiments as the available public data are not massive. However, we discuss a high-performance architecture that will be used if the collected data scales up dramatically. We compared our approach with the state-of-art methods by comparing most widely used metrics like Accuracy, Precision, Recall and F-measure. The proposed BERT + NBSVM outperformed alternative models by achieving 73% accuracy, 71% precision, 88% recall and 73% F-measure for classification of positive sentiments while 73% accuracy, 71% precision, 74% recall and 73% F-measure for classification of negative sentiments respectively. These promising results will be properly discussed in next sections. The use of artificial intelligence methods and social media analysis can lead to a better understanding of people's reactions and opinions about any trending topic. However, in the case of health-related topics like COVID-19 vaccines, proper sentiment identification could be crucial for implementing public health policies. More in detail, the availability of useful findings on user opinions about vaccines can help policymakers design proper strategies and implement ad-hoc vaccination protocols according to people's feelings, in order to provide better public service. To this end, we leveraged geospatial information to support effective recommendations for vaccination centers. [ABSTRACT FROM AUTHOR]

Whether it is an NLP (natural language processing) task or an NLU (natural language understanding) task, many methods are model oriented, ignoring the importance of data features. Such models did not perform well for many tasks based on feature loose, unbalanced tricky data including text classification tasks. In this regard, this paper proposes a classification method called LSTM-SN (long-short term memory RNN fusion social network) based on extremely complex datasets. The approach condenses the characteristics of the dataset. LSTM combines with social network methods derived from specific datasets to complete the classification task, and then use complex network structure evolution methods to discover dynamic social attributes. The experimental results show that this method can overcome the shortcomings of traditional methods and achieve better classification results. Finally, a method to calculate the accuracy of fusion model is proposed. The research ideas of this paper have far-reaching significance in the domain of social data analysis and relation extraction. [ABSTRACT FROM AUTHOR]

Machines can be equipped with the capability of identifying human emotions through conversation, thus enabling them to empathize with natural persons when they speak to them. The emergence of chatbots and intelligent assistants has led to a heightened focus on emotion recognition tasks. Most existing methodologies primarily focus on the isolated analysis of the speaker's attitudes and behaviors, thereby disregarding the essential interplay between the potential attitudes of interlocutors engaged in a specific conversation and their subsequent immediate dialogue behavior. As a result, the comprehension of the fundamental reasons behind the speaker's emotional fluctuations presents a noteworthy challenge throughout the course of the dialogue. This paper utilizes the attitude behavior theory from social psychology to develop a neural network model, namely the interaction neural network behind attitudes and behaviors of interlocutors for dialogue emotion recognition (DialogueINAB), that emulates the interactive process of the interlocutor's attitude and speech behavior in conversation. Our model presents new insights for recognizing emotions in conversations from a social psychology standpoint. DialogueINAB includes three modules: perception, information interaction, and emotion classifier. Initially, DialogueINAB identifies the features of potential attitudes and speech behaviors of the conversation interlocutors from the dialogue text. Second, by utilizing a crossmodal transformer architecture, the model can simulate the interaction between interlocutors' potential attitude and speech behavior and produce emotional features. Finally, the emotion classifier is supplied with the generated emotion features from the model for emotion recognition in conversation. We demonstrate the superiority of the proposed method through extensive experiments on three standard datasets (IEMOCAP, MELD, and AVEC). Compared with the six public baseline methods, our model improves the Weight-F1 metric by 3.56% and 1.04% on the IEMOCAP and MELD datasets and reduces the MAE metric by an average of 3.3% on the AVEC dataset. [ABSTRACT FROM AUTHOR]

Many attempts have been made to overcome the challenges of automating textual emotion detection using different traditional deep learning models such as LSTM, GRU, and BiLSTM. But the problem with these models is that they need large datasets, massive computing resources, and a lot of time to train. Also, they are prone to forgetting and cannot perform well when applied to small datasets. In this paper, we aim to demonstrate the capability of transfer learning techniques to capture the better contextual meaning of the text and as a result better detection of the emotion represented in the text, even without a large amount of data and training time. To do this, we conduct an experiment utilizing a pre-trained model called EmotionalBERT, which is based on bidirectional encoder representations from transformers (BERT), and we compare its performance to RNN-based models on two benchmark datasets, with a focus on the amount of training data and how it affects the models' performance. [ABSTRACT FROM AUTHOR]

System logs are an important data source for performance monitoring and anomaly detection. Analyzing logs for anomaly detection can improve service quality. At present, although machine learning algorithms for anomaly detection can achieve high accuracy, they lack robustness. The detection model cannot dynamically adapt to changes of logs when system logs contain noises owing to the casualness of the operators or log templates update. In face of this challenge, the paper proposes a robust log anomaly detection method based on contrastive learning and multi-scale Masked Sequence to Sequence (MASS). First, a log feature extraction model integrating the BERT model with contrastive learning is proposed. It can extract effective features by pulling two related normal logs together and pushing apart normal and abnormal logs to ensure that the semantic similarity between normal and abnormal log templates is lower than that between normal log templates, effectively remove abnormal log templates and distinguish log categories to which normal log templates and normal noise log templates belong rather than rudely treating the noise log templates as anomalies, which enhances the robustness of anomaly detection. Then, a multi-scale Masked Sequence to Sequence (MSMASS) model is proposed, the Attention mechanism of the MASS model is replaced with multi-scale Attention to fully learn the context information of different scales of the log sequence, which improves the accuracy of anomaly detection. Contrast experiments are conducted with four baseline methods on common datasets, and the results show that the method proposed in this paper is superior to most existing log-based anomaly detection methods in terms of accuracy and robustness. [ABSTRACT FROM AUTHOR]

Nowadays, the internet and social media ease the process of reviewing products. Consumers expose their thoughts, opinions, and experiences about products and services on various forums, websites, and mobile apps. In effect, internet reviews become a decision-maker for many people before getting their desired goods. Actually, text sentiment analysis consists of extracting insights and sentiments from social texts and consumers' reviews. Hence, various organizations conduct this analysis in order to better understand the attitude as well as the feedback of their customers toward their products. Besides, many scientific researchers are also interested in the analysis of customers' reviews by labeling them into a set of sentiments using some text classification algorithms. The following paper provides a convolutional neural network (CNN) model to classify text reviews' sentiments as negative or positive. Also, we make a comparative analysis using our proposed CNN model and several models' representations of word embedding to get the most efficient model. The experiments are implemented on the Amazon reviews dataset, and the diverse model designs have achieved appropriate performances. Reached results discern the importance of including stop-word in sentiment analysis tasks, in fact, the stop words elimination can provoke an inaccurate prediction of sentiments. Practically, using stop words with the CNN model has improved the accuracy result by 2% opposing the CNN model that has ignored them. Furthermore, we procure that the employment of a random initialization approach provides better performance than supervised and embedding model vectors on large-scale datasets. Effectively, training the representation of word embedding allows the model to learn better features in less computation time. Moreover, our CNN model showed better performance than the baseline machine learning and deep learning methods and improved the accuracy of the CNN to 90% on the Amazon reviews dataset. [ABSTRACT FROM AUTHOR]

Many military and business documents such as memorandums, invoices, medical records and bills among others are transmitted over the network in the form of images. These scanned document images may contain some private information that must not be accessed by third party or unauthorized users. Most of the encryption techniques encrypt the complete image but only parts of it require protection, which increases the computational and overhead communication cost. In this paper, we introduce a novel technique for selective multi-modal text recognition and encryption in scanned document images to overcome the issue of security and efficiency. Maximally stable extremal regions (MSER) are used in combination with two filtering techniques to automatically detect regions of interest (ROI) that contain text. Proposed technique combines optical character recognition (OCR) and natural language processing (NLP) in text recognition thus taking advantage of different modalities of data. Multi-modal recognized text is then encrypted using advanced encryption standard in cipher-block chaining mode (AES-CBC) and hybrid chaotic map. Simulation results illustrate the reliability and efficiency of proposed encryption scheme based on ROI. Moreover, security analysis exhibits the robustness of proposed encryption technique against linear and differential cryptographic attacks. [ABSTRACT FROM AUTHOR]

Rain impairs the performance of outdoor vision systems, such as automated driving systems and outdoor surveillance systems. Therefore, as an image preprocessing technique, image deraining has great potential for application. Defects of convolutional neural networks (small receptive field and non-adaptive to input content) limit the further improvement of deraining model performance. Recently, a novel neural network, transformer, has demonstrated impressive performance on natural language processing and vision tasks. However, using transformer for image deraining still has some issues: Although transformers have powerful long-range computing capabilities, it lacks the ability to model local features, which is critical for image deraining. In addition, transformer uses fixed-size patches to process images, which leads to pixels at the edges of the patches that cannot use the local features of neighboring pixels to restore rain-free images. In this paper, we propose a novel pyramid transformer for image deraining. To address the first issue, we design a residual-Dconv feed-forward network (RDFN), where depth-wise convolution improves the capability of modeling local features. To address the second issue, we introduce multi-resolution features into the transformer, which allows the transformer to obtain patches with different scales, thus enabling the boundary pixels to utilize local features. Furthermore, we propose a novel multi-scale fusion bridge (MSFB) to effectively integrate the extracted multi-scale features and capture the correlation between different scales. Extensive experiments on synthetic and real-world images demonstrate that the proposed deraining model achieves superior performance, especially the PSNR value achieves 47.55 dB on the SPA-Data dataset. We also further validate the effectiveness of the proposed model on subsequent high-level computer vision tasks. [ABSTRACT FROM AUTHOR]

The question answer (QA) system for a reading comprehension task tries to answer the question by retrieving the needed phrase from the given content. Precise answering is the key role of a QA system. An ambiguity is developed when we need to answer a negative question with a positive reply. The negation words change the polarity of the sentence, and hence, the scope of negation words is notable. This has paved the way for studying the role of 'negation' in the natural language processing (NLP) task. The handling of these words is considered a major part of our proposed methodology. In this paper, we propose an algorithm to retrieve and replace the negation words present in the content and query. A comparative study is done for performing word embedding over these words using various state-of-the-art methods. In earlier works when handling the negation the semantics of the sentences are changed. Hence, in this paper we try to maintain the semantics through our proposed methodology. The updated content is embedded into the bi-directional long short-term memory (Bi-LSTM) and thus makes the retrieving of an answer for a question answer system easier. The proposed work has been carried over the Stanford Negation, and the SQuAD dataset with a higher precision value of 96.2% has been achieved in retrieving the answers that are given in the dataset. [ABSTRACT FROM AUTHOR]

There has been a steep increase in the use of machine learning for various healthcare applications like the diagnosis of diseases, drug discovery, medical image analysis, etc. Machine learning solutions are proven to be more efficient and less time-consuming than conventional approaches. In this paper, we leverage the advantages of machine learning models to enable a humanoid robot to assist mental health patients. Facial expression and human voice are some of the most demonstrative ways to analyze human emotions, especially for the mentally challenged. We carry out this assistance by constantly monitoring the patient's voice (or audio) and facial expressions to predict human emotions. To implement the model of audio monitoring, we train three different machine learning and deep learning models to compare and choose the better model. Similarly, for facial recognition, we train a deep learning model using a specific dataset to predict facial expressions from the video captured in real time. We then integrate the better-performing machine learning models into a web interface for demonstration. [ABSTRACT FROM AUTHOR]

Due to the rapid growth of textual information on the web, analyzing users' opinions about particular products, events or services is now considered a crucial and challenging task that has changed sentiment analysis from an academic endeavor to an essential analytic tool in cognitive science and natural language understanding. Despite the remarkable success of deep learning models for textual sentiment classification, they are still confronted with some limitations. Convolutional neural network is one of the deep learning models that has been excelled at sentiment classification but tends to need a large amount of training data while it considers that all words in a sentence have equal contribution in the polarity of a sentence and its performance is highly dependent on its accompanying hyper-parameters. To overcome these issues, an Attention-Based Convolutional Neural Network with Transfer Learning (ACNN-TL) is proposed in this paper that not only tries to take advantage of both attention mechanism and transfer learning to boost the performance of sentiment classification but also language models, namely Word2Vec and BERT, are used as its the backbone to better express sentence semantics as word vector. We conducted our experiment on widely-studied sentiment classification datasets and according to the empirical results, not only the proposed ACNN-TL achieved comparable or even better classification results but also employing contextual representation and transfer learning yielded remarkable improvement in the classification accuracy. [ABSTRACT FROM AUTHOR]

Target-dependent sentiment classification is a fine-grained task of natural language processing to analyze the sentiment polarity of the targets. In order to address the difficulty of locating important sentiment information of targeted sentiment classification, recent research mostly applies attention mechanisms to capture the information of important context words, while the attention mechanism is subject to many drawbacks, e.g., dependent on network architecture and expensive. Recent studies show the significant effect of the local context focus (LCF) mechanism in capturing the relatedness between a target's sentiment and its local context. However, the LCF simply applies the fusion of global and local context features to classify sentiment, neglecting to empower the network to be aware of deep information of local context. In this paper, we propose a novel local context-aware network (LCA-Net) based on the local context embedding (LCE). Moreover, accompanied by the sentiment classification loss, the local context prediction (LCP) loss is proposed to enhance the LCE. The experimental results on three commonly used datasets, i.e., the Laptop and Restaurant datasets from SemEval-2014 and a Twitter social dataset, show that all the LCA-Net variants achieve promising performance improvement compared to existing approaches in extracting local context features. Besides, we implement the LCA-Net with different neural networks, validating the transferability of LCA architecture. [ABSTRACT FROM AUTHOR]

Online social network is one of the most prominent media that holds information about society's epidemic problem. Due to privacy reasons, most of the users will not disclose their location. Detecting the location of the tweet users is required to track the geographic location of the spreading diseases. This work aims to detect the spreading location of the COVID-19 disease from the Twitter users and content discussed in the tweet. COVID-19 is a disease caused by the "novel coronavirus." About 80% of confirmed cases recover from the disease. However, one out of every six people who get COVID-19 can become seriously ill, stated by the World health organization. Inferring the user location for identifying the spreading location for the disease is a very challenging task. This paper proposes a new technique based on a hypergraph model to detect the Twitter user's locations based on the spreading disease. This model uses hypergraph with weighting factor technique to infer the spreading disease's spatial location. The accuracy of prediction can be improved when a massive volume of streaming data is analyzed. The Helly property of the hypergraph was applied to discard less potential words from the text analysis, which claims this work of unique nature. A weighting factor was introduced to calculate the score of each location for a particular user. The location of each user is predicted based on the one that possesses the highest weighting factor. The proposed framework has been evaluated and tested for various measures like precision, recall and F-measure. The promising results obtained have substantiated the claim for this work compared to the state-of-the-art methodologies. [ABSTRACT FROM AUTHOR]

Sentiment lexicons in the English language are widely accessible while in many other languages, these resources are extremely deficient. Current techniques and methods for sentiment analysis focus mainly on the English language, whereas other languages are neglected due to lack of resources. In order to overcome challenges faced in building non-English lexicons, we propose a language-independent method that automatically builds non-English sentiment lexicons based on currently available English lexicons with an unannotated corpus from the target language. The proposed method will automatically recognize and extract new polarity words from the unannotated corpus based on the initial seed lexicons that are developed by translating three reliable English lexicons. The experimental results from the test datasets confirmed that a developed non-English sentiment lexicon could significantly enhance the performance of non-English sentiment classifications, compared with other methods and lexicons. The developed lexicon in the Arabic language outperformed other commonly used methods for developing non-English lexicons, with an 0.74 F measure. The adopted approach in this study was proven to be language independent and can be implemented in other languages as well. This paper also contributes to understanding the approaches to developing sentiment resources. [ABSTRACT FROM AUTHOR]

The objective of an emergency call is to provide the operator with as much pertinent information about the emergency as possible, so that the best course of action can be taken toward its resolution. In this paper, we propose a dialogue planner to support operators who take emergency calls. The proposed system helps the operators to respond appropriately to a caller’s report by planning potential follow-up dialogue. The decision-making process used by the planner to select from among the proposed actions is implemented as a finite-state machine. The planner assigns a weight to each path between the states, evaluates the current dialogue model, and then adjusts the weights accordingly. Therefore, the weights assigned to potential actions vary dynamically as the dialogue progresses. The proposed model guides the operators’ decisions throughout each conversation by informing them regarding the action that has the highest weighting. [ABSTRACT FROM AUTHOR]