Using Data Mining, Text Mining, and Bibliometric Techniques to the Research Trends and Gaps in the Field of Language and Linguistics

This study adopted descriptive and explorative methods to analyze 2162 published documents, in general, and 1903 articles, in particular, in System from 1973 to 2020 based on the Scopus database. Data preprocessing and analysis were performed using data mining, text mining, and bibliometric techniques through Excel, VOSviewer, and RapidMiner software. To analyze the article titles and identify their themes, N-Grams was considered among the text mining techniques. From the data mining techniques, clustering was applied to explore the clusters of languages, educational technologies, technological spaces for foreign languages, etc. Bibliometric techniques such as co-authorship networks and citation analysis were in turn used to analyze the tops and trends of research in System. The results are classified into 5 categories including: (1) journal status; (2) publication trend; (3) articles with and without abstract/keyword; (4) highly-cited and uncited articles; (5) core and poor topics and keywords. The core topics are English as a Foreign Language, motivation, and second language acquisition. Among the languages, English, Chinese, and Japanese are at the top, and Italian, Danish, Persian, and Taiwanese are less discussed. Based on the findings, System has moved in line with its goals and scope, which are the applications of educational technology and applied linguistics to solve the problems of foreign language teaching and learning.