Opinion Mining and Sentiment Analysis Using Deep Neural Network

Dear Colleagues,

Opinion Mining and Sentiment Analysis systems constitute gigantic data, flowing continuously out of social networks. Opinion Mining and Sentiment Analysis driven techniques are used in diverse domains, including science, technology, business and education. Key requirements for such approaches include the efficient detection and classification of information that can be acquired from social networking content, even in the presence of noisy streams. Although many approaches to offline and real-time Opinion Mining and Sentiment Analysis systems are already in use, many issues and challenges need to be addressed.

Traditional machine learning algorithms for opinion mining and sentiment analysis employ conventional feature representation schemes, followed by a classifier. Such procedures are ineffective, prompting researchers to create more robust methods. To address the limits of traditional methodologies, deep-learning-based opinion mining and sentiment analysis techniques should be employed, which have already demonstrated a promising performance across a wide range of complex issues in domains such as vision, speech, and text analytics.

In this special Section, our focus will be on extracting, classifying and evaluating valuable information from social media conten that are huge, vague, sparse, and sustainable, and assemble it smoothly within the frame of practical, sentiment-based software applications. In other words, we welcome contributions demonstrating how online information is transformed into useful and reliable information that is easily interpreted for diverse purposes, such as decision making, prediction, business intelligence, health care, rumor detection, intention mining, extremist’s affiliation identification and others.

Areas of interest include, but are not limited to:

• Role and importance of opinion mining and sentiment analysis in information processing;
• Data Acquisition and Benchmark preparation for offline and real-time text streaming;
• Noise reduction techniques and challenges in processing opinion mining and sentiment analysis;
• Architecture design for sentiment classification of social networking information management systems;
• Deep Learning models for efficient classification of social networking information management systems;
• Social-network-based opinion mining and sentiment analysis for  prediction, decision making and disaster management;
• Challenges and solutions when disambiguating multiple forms of opinion mining and sentiment analysis systems (text streams);
• Emotion and personality recognition in opinion mining and sentiment analysis systems (text, images, audio and video) and its applications for detecting extremist affiliations;
• Opinion mining and sentiment analysis systems models for detecting malicious information propagation;
• Issues, challenges and their solutions when developing computational models and tools for fake news detection and classification;
• Mining social media text to classify human intentions and its applications in business intelligence;
• Deep-learning-driven E-learning and social networking;
• Developing deep-learning-based opinion mining and sentiment analysis  applications for resource-poor languages;
• Development of Cloud Computing models for opinion mining and sentiment analysis systems;
• Feature Engineering for Developing opinion mining and sentiment analysis systems processing; 
• Challenges and solutions when developing multilingual sentiment-based software applications;
• Creating innovative lexical resources for sentiment analysis in multiple languages;
• Emerging issues in social-network-based opinion mining and sentiment analysis systems, such irony detection, implicit intentions, and spamicity detection;
• Multimedia content classification acquired from opinion mining and sentiment analysis systems;
• Context-aware concept-level sentiment mining;
• Handling uncertainty in sentiment analyzers using fuzzy, rough set and other theories;
• Ontology-based sentiment analysis applications;
• Investigating deep neural networks in social computing;
• Development of opinion mining and sentiment analysis systems based on depthwise convolutional networks;
• Development of opinion mining and sentiment analysis systems based on federated learning.

Dr. Muhammad Zubair Asghar
Dr. Asad Masood
Prof. Dr. Shakeel Ahmad
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.