Human-Computer Interaction: A Literature Analysis from 1998 to 2018 Using Automated Text Mining

The purpose of this study is to investigate the research themes and trends in the field of Human-Computer Interaction (HCI) in the last twenty years between 1998-2018. For this purpose, an automated text mining based content analysis has been implemented using probabilistic topic modeling on 33830 peer-reviewed journal articles published between 1998-2018, and that are indexed by SCOPUS database. As a result of this analysis, 53 topics specifying the themes and trends in the HCI field was uncovered. Besides, these discovered topics categorized within themselves, and a systematic taxonomy mapping the landscape of HCI research and practices in the past 20 years was presented. This taxonomy contains six main categories: "machinery systems", "HCI body of knowledge", "feature identification", "brain-computer interfaces", "interaction", and "medical". This study is expected to contribute to HCI research, practices, and investments in the future.