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.

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.

In this book, we explored a code implementation for sentiment analysis using machine learning models, including XGBoost, LightGBM, and LSTM. The code aimed to build, train, and evaluate these models on Twitter data to classify sentiments. Throughout the project, we gained insights into the key steps involved and observed the findings and functionalities of the code. Sentiment analysis is a vital task in natural language processing, and the code was to give a comprehensive approach to tackle it. The implementation began by checking if pre-trained models for XGBoost and LightGBM existed. If available, the models were loaded; otherwise, new models were built and trained. This approach allowed for reusability of trained models, saving time and effort in subsequent runs. Similarly, the code checked if preprocessed data for LSTM existed. If not, it performed tokenization and padding on the text data, splitting it into train, test, and validation sets. The preprocessed data was saved for future use. The code also provided a function to build and train the LSTM model. It defined the model architecture using the Keras Sequential API, incorporating layers like embedding, convolutional, max pooling, bidirectional LSTM, dropout, and dense output. The model was compiled with appropriate loss and optimization functions. Training was carried out, with early stopping implemented to prevent overfitting. After training, the model summary was printed, and both the model and training history were saved for future reference. The train_lstm function ensured that the LSTM model was ready for prediction by checking the existence of preprocessed data and trained models. If necessary, it performed the required preprocessing and model building steps. The pred_lstm() function was responsible for loading the LSTM model and generating predictions for the test data. The function returned the predicted sentiment labels, allowing for further analysis and evaluation. To facilitate user interaction, the code included a functionality to choose the LSTM model for prediction. The choose_prediction_lstm() function was triggered when the user selected the LSTM option from a dropdown menu. It called the pred_lstm() function, performed evaluation tasks, and visualized the results. Confusion matrices and true vs. predicted value plots were generated to assess the model's performance. Additionally, the loss and accuracy history from training were plotted, providing insights into the model's learning process. In conclusion, this project provided a comprehensive overview of sentiment analysis using machine learning models. The code implementation showcased the steps involved in building, training, and evaluating models like XGBoost, LightGBM, and LSTM. It emphasized the importance of data preprocessing, model building, and evaluation in sentiment analysis tasks. The code also demonstrated functionalities for reusing pre-trained models and saving preprocessed data, enhancing efficiency and ease of use. Through visualization techniques, such as confusion matrices and accuracy/loss curves, the code enabled a better understanding of the model's performance and learning dynamics. Overall, this project highlighted the practical aspects of sentiment analysis and illustrated how different machine learning models can be employed to tackle this task effectively.

Besides learning the low-level local features, higher level representations are further designed to be learned in the context of applications. The data-driven concept representations and sparse representation of the events are learned for complex event recognition; the representations for object body parts and structures are learned for object detection in videos; and the relational motion features and similarity metrics between video pairs are learned simultaneously for action verification. Second, in order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: first it optimizes both discriminative and generative properties of the features simultaneously, which gives our features a better discriminative ability. Second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experiments with quantitative and qualitative results on the tasks of human detection and action verification demonstrate the superiority of our proposed models.

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 book constitutes the proceedings of the 10th International Conference on Artificial Intelligence and Mobile Services, AIMS 2021, held as a virtual conference as part of SCF 2021, during December 10-14, 2021. The 9 full presented were carefully reviewed and selected from 20 submissions. They cover topics in AI Modeling, AI Analysis, AI and Mobile Applications, AI Architecture, AI Management, AI Engineering, mobile backend as a service (MBaaS), user experience of AI and mobile services.