Semantic Web Technologies for Sentiment Analysis

A special issue of Future Internet (ISSN 1999-5903).

Deadline for manuscript submissions: closed (30 July 2019)

Special Issue Information

Dear Colleagues,

With the widespread of Internet and the web, interactions, sharing, and collaborations through social networks, online communities, blogs, etc. are becoming daily tasks for users who have already become enthusiastic about the several services and opportunities these offer. Several domains have been 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, sarcasm), and modalities (e.g., doubt, certainty, obligation, liability, 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 a growing amount of interest, both in 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) sentiment associated with companies and stocks. One more is related to emotion detection, whose task is, given a set of texts, to identify which emotion conveys 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 give up on seeking different opinions and platforms that struggle to effectively facilitate conversations, avoiding problems like those.

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, 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 that, 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:

  • 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, robotics).

The special issue is linked with the Fifth International Workshop at ESWC on Sentic Computing, Sentiment Analysis, Opinion mining and Emotion Detection which reflects the challenges, and the topics of the special issue.

The workshop aims at addressing the above mentioned challenges by providing a forum for researchers and practitioners to discuss, exchange and disseminate their solutions.


Organizers: Diego Reforgiato Recupero and Mauro Dragoni

Besides, the special issue "Semantic Web Technologies for Sentiment Analysis" would like to advertise the call for PhD application for a Marie Curie Innovative Training Network (European Industrial Doctorate) within the project PhilHumans, Personal Health Interfaces Leveraging HUman-MAchine Natural interactionS. In short, The goal of the PhilHumans project is to train a next generation of young researchers (Early Stage Researcher) in innovative Artificial Intelligence (AI) and establish user interaction with their personal health devices in an advanced and intuitive way. The project will explore cutting-edge research topics related to AI-supported human-machine interfaces for personal health services. There are 8 PhD positions available. One of them is focused and related to the Semantic Sentiment Analysis and the topics covered by the special issue, Prof. Reforgiato will supervise this PhD candidate and the University of Cagliari will be the hosting organization. Please check further details within the project website and apply using the website.

Dr. Diego Reforgiato Recupero
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at 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

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


13 pages, 3694 KiB  
Incorporating Background Checks with Sentiment Analysis to Identify Violence Risky Chinese Microblogs
Future Internet 2019, 11(9), 200; - 19 Sep 2019
Cited by 5 | Viewed by 2763
Based on Web 2.0 technology, more and more people tend to express their attitude or opinions on the Internet. Radical ideas, rumors, terrorism, or violent contents are also propagated on the Internet, causing several incidents of social panic every year in China. In [...] Read more.
Based on Web 2.0 technology, more and more people tend to express their attitude or opinions on the Internet. Radical ideas, rumors, terrorism, or violent contents are also propagated on the Internet, causing several incidents of social panic every year in China. In fact, most of this content comprises joking or emotional catharsis. To detect this with conventional techniques usually incurs a large false alarm rate. To address this problem, this paper introduces a technique that combines sentiment analysis with background checks. State-of-the-art sentiment analysis usually depends on training datasets in a specific topic area. Unfortunately, for some domains, such as violence risk speech detection, there is no definitive training data. In particular, topic-independent sentiment analysis of short Chinese text has been rarely reported in the literature. In this paper, the violence risk of the Chinese microblogs is calculated from multiple perspectives. First, a lexicon-based method is used to retrieve violence-related microblogs, and then a similarity-based method is used to extract sentiment words. Semantic rules and emoticons are employed to obtain the sentiment polarity and sentiment strength of short texts. Second, the activity risk is calculated based on the characteristics of part of speech (PoS) sequence and by semantic rules, and then a threshold is set to capture the key users. Finally, the risk is confirmed by historical speeches and the opinions of the friend-circle of the key users. The experimental results show that the proposed approach outperforms the support vector machine (SVM) method on a topic-independent corpus and can effectively reduce the false alarm rate. Full article
(This article belongs to the Special Issue Semantic Web Technologies for Sentiment Analysis)
Show Figures

Figure 1

Back to TopTop