Text Classification Using Word Embedding in Rule-Based Methodologies: A Systematic Mapping

Abstract

With the advancing growth of the World Wide Web (WWW) and the expanding availability of electronic text documents, the automatic assignment of text classification (ATC) has become more important in sorting out information and knowledge. One of the most crucial tasks that should be carried out is document representation using word embedding and Rule-Based methodologies. As a result, this, along with their modeling methods, has become an essential step to improve neural language processing for text classification. In this paper, a systematic mapping study is a way to survey all the primary studies on word embedding to rule-based and machine learning of automatic text classification. The search procedure identifies 20 articles as relevant to answer our research questions. This study maps what is currently known about word embedding in rule-based text classification (TC). The result shows that the research is concentrated on some main areas, mainly in social sciences, shopping products classification, digital libraries, and spam filtering. The present paper contributes to the available literature by summarizing all research in the field of TC and it can be beneficial to other researchers and specialists in order to sort information.