Short Text Mining: State of the Art and Research Opportunities

Abstract

With the growing number of connected online users producing a tremendous amount of unstructured short-texts daily, understanding and mining these data becomes very useful for individuals, governments and companies for identifying the public users’ attitudes towards different entities, such as products, services, events, places, organizations and topics. However, analyzing these short-texts using traditional methods becomes a significant challenge due to the shortness and sparsity nature of short-texts. To address such challenges, the literature introduced a broad spectrum of short-texts mining approaches and applications. Hence, this paper provides a comprehensive survey of this spectrum based on a criterion-based research strategy. The different mining techniques and approaches utilized in short-texts were highlighted along with their related issues and challenges. This paper surveyed a total of 1575 research papers published in the refereed conferences and journals in the area of short-texts mining were sur-veyed from 2006 until 2017, from which 187 primary studies were included and analyzed to constitute the source of the present paper. After a careful review of these articles, it is obvious that there are research gaps in other languages than English and Chinese, multi-languages, and in specific domain studies.