Semantic Web Technologies for the Sentiment Analysis

Dear Colleagues, 

With the widespread growth of the Internet, interactions, sharing, and collaborations through social networks, online communities, blogs, etc., are becoming daily activities for users, who have become enthusiastic about their many possibilities. Several domains are affected, in particular those related to e-commerce, tourism, education, and health. Plenty of data (big data) are therefore generated, and the need for automatic tools that process textual data, generating analysis, warnings, summaries, and recommendations is increasing. In particular, identifying sentiments, emotions (such as sadness, happiness, anger, irony, and sarcasm), and modalities (e.g., doubt, certainty, obligation, liability, and desire) has become key to correctly interpreting opinions reported about social events, interactions, political campaigns, company strategies, marketing campaigns, product preferences, and others.

This has provided new research challenges and applications, thus creating growing interest in both the scientific community and in the business world. One example is provided by the financial domain, where one of the goals is to identify, given a set of financial texts, bullish (optimistic, meaning that the stock price will increase) and bearish (pessimistic, meaning that the stock price will decrease) sentiments associated with companies and stocks. Another example is related to emotion detection, whose task is, when given a set of texts, to identify which emotion is conveyed by each of them out of a number of defined emotions. A third example is provided by aspect-based sentiment analysis, whose task is to find an opinion related to a certain feature (aspect) of a given topic. A further example is provided by the identification of toxicity levels of blog messages, which is important because it causes people to stop expressing themselves and to give up on seeking different opinions and platforms that struggle to effectively facilitate conversations, thus avoiding such problems.

To address those problems, tools using simple statistical approaches emerged several years ago, with performances depending on the complexity of the underlying problem.

When semantic web technologies (lexical and semantic resources, word embeddings, machine readers, and ontologies) arose, they strengthened the existing tools of natural language processing (NLP), bringing innovations and benefits to a wide set of domains, including sentiment analysis. The hybridization of NLP techniques with semantic web technologies has thus become a direction worth exploring, and has already provided several improvements over classical statistical approaches. Moreover, the combination of semantic web technologies and resources with deep learning approaches has enabled the development of frameworks that have further improved precision–recall analysis for existing problems within the sentiment analysis domain.

Based on all of this, this Special Issue aims at collecting novel, exciting papers reporting the most recent advances in sentiment analysis techniques, where semantic web technologies play a key role in improving the performances of the underlying approach. Topics of interest include, but are not limited to, the following: 

• Ontologies and knowledge bases for emotion recognition;
• Topic- and entity-based emotion recognition;
• Semantics in the evolution of emotions within and across social media systems and topics;
• Semantic processing of social media for emotion recognition;
• Contextualized emotion recognition;
• Comparison of semantic approaches for emotion recognition;
• Personalized semantic emotion recognition and monitoring;
• Using semantics for prediction of emotions towards events, people, organizations, etc.;
• Baselines and datasets for semantic emotion recognition;
• Semantics in stream-based emotion recognition;
• Comparison between semantic and nonsemantic approaches for emotion recognition;
• Multimodal emotion recognition;
• Multilingual sentiment analysis;
• Challenges in using semantics for emotion recognition;
• Retrieval of emotion-based documents from repositories;
• Deep learning and knowledge-enabled approaches for sentiment analysis;
• Big data tools and techniques for sentiment analysis;
• Applications of sentiment analysis within specific domains (e.g., health and robotics). 

Prof. Dr. Diego Reforgiato Recupero
Guest Editor

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. Future Internet is an international peer-reviewed open access monthly 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 1600 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.

• semantic web
• sentiment analysis
• natural language processing
• deep learning
• big data