This book presents the latest research on hierarchical deep learning for multi-modal sentiment analysis. Further, it analyses sentiments in Twitter blogs from both textual and visual content using hierarchical deep learning networks: hierarchical gated feedback recurrent neural networks (HGFRNNs). Several studies on deep learning have been conducted to date, but most of the current methods focus on either only textual content, or only visual content. In contrast, the proposed sentiment analysis model can be applied to any social blog dataset, making the book highly beneficial for postgraduate students and researchers in deep learning and sentiment analysis. The mathematical abstraction of the sentiment analysis model is presented in a very lucid manner. The complete sentiments are analysed by combining text and visual prediction results. The book’s novelty lies in its development of innovative hierarchical recurrent neural networks for analysing sentiments; stacking of multiple recurrent layers by controlling the signal flow from upper recurrent layers to lower layers through a global gating unit; evaluation of HGFRNNs with different types of recurrent units; and adaptive assignment of HGFRNN layers to different timescales. Considering the need to leverage large-scale social multimedia content for sentiment analysis, both state-of-the-art visual and textual sentiment analysis techniques are used for joint visual-textual sentiment analysis. The proposed method yields promising results from Twitter datasets that include both texts and images, which support the theoretical hypothesis.
This book features research papers presented at the International Conference on Emerging Technologies in Data Mining and Information Security (IEMIS 2020) held at the University of Engineering & Management, Kolkata, India, during July 2020. The book is organized in three volumes and includes high-quality research work by academicians and industrial experts in the field of computing and communication, including full-length papers, research-in-progress papers and case studies related to all the areas of data mining, machine learning, Internet of things (IoT) and information security.
This book covers deep-learning-based approaches for sentiment analysis, a relatively new, but fast-growing research area, which has significantly changed in the past few years. The book presents a collection of state-of-the-art approaches, focusing on the best-performing, cutting-edge solutions for the most common and difficult challenges faced in sentiment analysis research. Providing detailed explanations of the methodologies, the book is a valuable resource for researchers as well as newcomers to the field.
The natural interaction ability between human and machine mainly involves human-machine dialogue ability, multi-modal sentiment analysis ability, human-machine cooperation ability, and so on. To enable intelligent computers to have multi-modal sentiment analysis ability, it is necessary to equip them with a strong multi-modal sentiment analysis ability during the process of human-computer interaction. This is one of the key technologies for efficient and intelligent human-computer interaction. This book focuses on the research and practical applications of multi-modal sentiment analysis for human-computer natural interaction, particularly in the areas of multi-modal information feature representation, feature fusion, and sentiment classification. Multi-modal sentiment analysis for natural interaction is a comprehensive research field that involves the integration of natural language processing, computer vision, machine learning, pattern recognition, algorithm, robot intelligent system, human-computer interaction, etc. Currently, research on multi-modal sentiment analysis in natural interaction is developing rapidly. This book can be used as a professional textbook in the fields of natural interaction, intelligent question answering (customer service), natural language processing, human-computer interaction, etc. It can also serve as an important reference book for the development of systems and products in intelligent robots, natural language processing, human-computer interaction, and related fields.
Images play a crucial role in shaping and reflecting political life. Digitization has vastly increased the presence of such images in daily life, creating valuable new research opportunities for social scientists. We show how recent innovations in computer vision methods can substantially lower the costs of using images as data. We introduce readers to the deep learning algorithms commonly used for object recognition, facial recognition, and visual sentiment analysis. We then provide guidance and specific instructions for scholars interested in using these methods in their own research.
Deep learning and reinforcement learning are some of the most important and exciting research fields today. With the emergence of new network structures and algorithms such as convolutional neural networks, recurrent neural networks, and self-attention models, these technologies have gained widespread attention and applications in fields such as natural language processing, medical image analysis, and Internet of Things (IoT) device recognition. This book, Deep Learning and Reinforcement Learning examines the latest research achievements of these technologies and provides a reference for researchers, engineers, students, and other interested readers. It helps readers understand the opportunities and challenges faced by deep learning and reinforcement learning and how to address them, thus improving the research and application capabilities of these technologies in related fields.
Establishing the means to improve performance in healthy, clinical, and military populations has long been a focus of study in the psychological and brain sciences. However, a major obstacle to this goal is generating individualized performance phenotypes that allow for the design of interventions that are tailored to the specific needs of the individual. Recent developments in artificial intelligence (AI) have qualified for the development of precision approaches that consider individual differences, allowing, for example, the establishment of individualized training, preparation, and recuperation programs optimal for an individual’s cognitive and biological phenotype. Corollary developments in AI have proven that combining domain expertise and stakeholder insights can considerably improve AI’s quality, performance, and dependability in the psychology and brain sciences. Recent Developments in Machine and Human Intelligence studies original empirical work, literature reviews, and methodological papers that establish and validate precision AI methods for human performance optimization with a focus on modeling individual differences via state-of-the-art computational methods and investigating how domain expertise and human judgment can improve the performance of AI methods. The topics are crafted in such a way as to cover all the areas of artificial and human intelligence that require AI for further development. This book contains algorithms and techniques that are explained with the help of developed source code and encompasses the readiness and needs for advancements in managing yet another pandemic in the future. It is designed for academicians, scientists, research scholars, professors, graduates, undergraduates, and students.
This thesis focuses on two Natural Language Processing tasks that require to extract semantic information from raw texts: Sentiment Analysis and Text Summarization. This dissertation discusses issues and seeks to improve neural models on both tasks, which have become the dominant paradigm in the past several years. Accordingly, this dissertation is composed of two parts: the first part (Neural Sentiment Analysis) deals with the computational study of people's opinions, sentiments, and the second part (Neural Text Summarization) tries to extract salient information from a complex sentence and rewrites it in a human-readable form. Neural Sentiment Analysis. Similar to computer vision, numerous deep convolutional neural networks have been adapted to sentiment analysis and text classification tasks. However, unlike the image domain, these studies are carried on different input data types and on different datasets, which makes it hard to know if a deep network is truly needed. In this thesis, we seek to find elements to address this question, i.e. whether neural networks must compute deep hierarchies of features for textual data in the same way as they do in vision. We thus propose a new adaptation of the deepest convolutional architecture (DenseNet) for text classification and study the importance of depth in convolutional models with different atom-levels (word or character) of input. We show that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outperforms the deep DenseNet models with word inputs. Besides, to further improve sentiment classifiers and contextualize them, we propose to model them jointly with dialog acts, which are a factor of explanation and correlate with sentiments but are nevertheless often ignored. We have manually annotated both dialogues and sentiments on a Twitter-like social medium, and train a multi-task hierarchical recurrent network on joint sentiment and dialog act recognition. We show that transfer learning may be efficiently achieved between both tasks, and further analyze some specific correlations between sentiments and dialogues on social media. Neural Text Summarization. Detecting sentiments and opinions from large digital documents does not always enable users of such systems to take informed decisions, as other important semantic information is missing. People also need the main arguments and supporting reasons from the source documents to truly understand and interpret the document. To capture such information, we aim at making the neural text summarization models more explainable. We propose a model that has better explainability properties and is flexible enough to support various shallow syntactic parsing modules. More specifically, we linearize the syntactic tree into the form of overlapping text segments, which are then selected with reinforcement learning (RL) and regenerated into a compressed form. Hence, the proposed model is able to handle both extractive and abstractive summarization. Further, we observe that RL-based models are becoming increasingly ubiquitous for many text summarization tasks. We are interested in better understanding what types of information is taken into account by such models, and we propose to study this question from the syntactic perspective. We thus provide a detailed comparison of both RL-based and syntax-aware approaches and of their combination along several dimensions that relate to the perceived quality of the generated summaries such as number of repetitions, sentence length, distribution of part-of-speech tags, relevance and grammaticality. We show that when there is a resource constraint (computation and memory), it is wise to only train models with RL and without any syntactic information, as they provide nearly as good results as syntax-aware models with less parameters and faster training convergence.
As the amount of unstructured text data that humanity produces overall and on the Internet grows, so does the need to intelligently process it and extract different types of knowledge from it. My research goal in this thesis is to develop learning models that can automatically induce representations of human language, in particular its structure and meaning in order to solve multiple higher level language tasks. There has been great progress in delivering technologies in natural language processing such as extracting information, sentiment analysis or grammatical analysis. However, solutions are often based on different machine learning models. My goal is the development of general and scalable algorithms that can jointly solve such tasks and learn the necessary intermediate representations of the linguistic units involved. Furthermore, most standard approaches make strong simplifying language assumptions and require well designed feature representations. The models in this thesis address these two shortcomings. They provide effective and general representations for sentences without assuming word order independence. Furthermore, they provide state of the art performance with no, or few manually designed features. The new model family introduced in this thesis is summarized under the term Recursive Deep Learning. The models in this family are variations and extensions of unsupervised and supervised recursive neural networks which generalize deep and feature learning ideas to hierarchical structures. The RNN models of this thesis obtain state of the art performance on paraphrase detection, sentiment analysis, relation classification, parsing, image-sentence mapping and knowledge base completion, among other tasks.
This latest volume in the series, Socio-Affective Computing, presents a set of novel approaches to analyze opinionated videos and to extract sentiments and emotions. Textual sentiment analysis framework as discussed in this book contains a novel way of doing sentiment analysis by merging linguistics with machine learning. Fusing textual information with audio and visual cues is found to be extremely useful which improves text, audio and visual based unimodal sentiment analyzer. This volume covers the three main topics of: textual preprocessing and sentiment analysis methods; frameworks to process audio and visual data; and methods of textual, audio and visual features fusion. The inclusion of key visualization and case studies will enable readers to understand better these approaches. Aimed at the Natural Language Processing, Affective Computing and Artificial Intelligence audiences, this comprehensive volume will appeal to a wide readership and will help readers to understand key details on multimodal sentiment analysis.
