Assessment Approach to the Interconnections of Social Network Radical Online Communities Based on Open Data Analysis with the Use of TF-IDF

Online-radicalization researches automation is considered to be one of the currently important tasks of contemporary sociology. On one side, the Internet data accessibility, including social networks data, provides unique opportunities from the perspective of coverage of the phenomena and processes under study. On the other side, notwithstanding the increased availability of Data Science tools, the potency of their use depends equally on both the corresponding skills and the applied subject area competence. The present work introduces the experience of an interdisciplinary research group in adapting and applying the automated data harvesting and preprocessing tools of online radicalization. Assessment toolkit of words relevancy in posts has been considered on the basis of TF-IDF statistical measure. The hypothesis about the closedness of radical on-line communities in "echo-chambers" has been verified and partially confirmed.