Identifying Content-Related and Non-content-related Queries in Online Discussion Forums Using Voyant Tools

The overarching goal of this study was to assess the suitability of Voyant Tools to identify the frequency of content-related and non-content-related query subjects (thread title) and prioritize them based on their occurrence and importance in the online discussion forum. The dataset consisted of 296 query subjects collected from the discussion forums of practical and theoretical massive open online courses (MOOCs). The cirrus, correlation, and scatter plot features of Voyant Tools (a web-based application) were used to analyze the dataset. The Cirrus feature assisted with word frequency, and the Correlation feature helped with their co-occurrence in the online discussion forum. The Scatter plot feature was the most appropriate tool among the three tools implemented in the current study for generating the clusters of content-related and non-content-related query subjects. Overall, Voyant Tools was an effective resource capable of analyzing quantitative and qualitative data and providing visual output in various forms.