The World Wide Web is becoming a bottomless source of unstructured data, with quintillions of bytes of data generated daily and publicly accessible. Social media, customer reviews and online news articles, as well as the comments associated with them, are just some examples of what the Internet is producing in terms of text data. At the same time, the World Wide Web is providing us with a great source of information about user behaviors and preferences. This has led soft computing techniques to have unmatched growth in the fields of text mining and sentiment analysis, which are adapted and applied to applications such as recommender systems. The main challenge of such systems is to filter and transform busy online information streams into structured data that can be used for decision-making.
Most of the work on social media analysis has focused on textual data. The application of techniques like text mining or knowledge discovery has given birth to an important number of new different areas such as opinion retrieval, opinion summarization, subjectivity classification, among others. Furthermore, most of these textual data may also represent implicit or explicit user feedback, expressed in different formats, such as star ratings and Facebook likes, and collected from multiple sources. The combination of such multifaceted information allows for the development of new tools for recommending items according to aspects such as reputation, trust, credibility, fame, etc.
Sentiment analysis techniques have provided powerful tools for decision-making in different fields, including politics, marketing, and healthcare. Some sectors also provide ad-hoc functionalities like in the case of Stocktwits, in the context of financial markets, and LinkedIn, in the context of human resources. Moreover, different soft computing techniques, such as deep neural networks and linguistic fuzzy logic, have been increasingly adopted for natural language processing and knowledge representation. Such techniques have gained increasing momentum in the past years, with a remarkable enhancement of their accuracy, and they have been sided by a boost in application-specific methodologies able to emulate the cognitive processes behind decision-making.
In this special issue on soft computing for sentiment analysis and recommender systems, we aim to address the following issues:
Combination of soft computing and natural language processing techniques for the development of sentiment analysis and recommender systems.
Application of the recent artificial intelligence and soft computing techniques to social media mining and knowledge representation.
Design and development of specific methodologies for social media analytics in the context of sentiment analysis and recommender systems.
Topics of Interest
Topics of interest include, but are not limited to:
Community discovery and analysis in social networks.
Visualization or structural analysis of social networks.
Clustering and graph mining algorithms for social media.
Descriptive and linguistic analysis of social media data.
High-dimensional analysis of social media data.
Analysis of reputation, credibility, and trust on social media data.
Opinion search and meta-search.
Fuzzy linguistic techniques for recommender systems.
Applications of sentiment analysis and recommender systems: stock market prediction, portfolio optimization and asset allocation, trading strategies, labor market intelligence, e-commerce, e-learning, and social media marketing.
Submission starting: December 1st, 2019
First notification: 3 months
Submission closing: June 30th, 2020
Paper submissions for the special issue should follow the submission format and guidelines for regular papers and submitted at https://ees.elsevier.com/asoc. All the papers will be peer-reviewed following Applied Soft Computing reviewing procedures. Guest editors will make an initial assessment of the suitability and scope of all submissions. Papers will be evaluated based on their originality, presentation, relevance and contributions, as well as their suitability to the special issue. Papers that either lack originality, clarity in presentation or fall outside the scope of the special issue will not be sent for review. Authors should select “SI: Sentiment Analysis” when they reach the “Article Type” step in the submission process. The submitted papers must propose original research that has not been published nor currently under review in other venues. Previously published conference papers should be clearly identified by the authors at the submission
stage and an explanation should be provided about how such papers have been extended. Such contributions must have at least 50% difference from the research work they stem from.