Special Issue on Sentiment on Social Web & Social Computing - Data Science for the Social Web
• 大类 : 工程技术 - 2区
• 小类 : 计算机：理论方法 - 2区
In today’s era, every day 2.5 quintillion bytes of data has been generated which is an unimaginable number to human beings. Thanks to the efforts of researcher and developers in continual development of big data techniques, platform and architectures, handling and processing big data become more achievable. There is vast amount of useful information and knowledge that could be extracted from raw (unstructured) data in both public and private sectors, via two important concepts: semantic and sentiment analysis.
Semantic analysis focuses on the study of dataset under various logical meanings and clusters as well as extraction of relevant meanings from the given dataset. On the other hand, sentiment analysis aims at identifying and extracting opinions within dataset, and creating typical attributes of opinion holder, subject and polarity. The analysis offers attractive advantages of scalability, real-time, consistent criteria (avoid human bias) and leads to an increase popularity in market research, product analytics, workforce analytics, customer service, voice of customer/employee, brand analytics and social media monitoring. There are several main challenges that are subjected to further research, for instance, subjectivity and tone, context and polarity, irony and sarcasm, comparison, emojis, and definition of neutral.
This special issue is intended to report high-quality and original research on semantic and sentiment analysis including emerging trends and technologies, with results and discussion via practical applications and case studies. Topics include but are not limited to:
• Semantic and sentiment analysis of social media/network
• Big data architectures for semantic and sentiment applications
• Rule-based, automatic and hybrid approach for semantic and sentiment analysis
• Deep learning approach for semantic and sentiment analysis
• Reliability model for near future context and polarity predictions
• Semantic and sentiment analysis in document level, sentence level and sub-sentence level
• Figure of merits for semantic and sentiment analysis
• Modalities and heterogeneity: multi-modal and cross-modal analysis