Text Mining for Information Systems Researchers: An Annotated Topic Modeling Tutorial

The Tale of e-Government: A Review of the Stories that Have Been Told So Far and What is Yet to Come

“…This is in line with another recommendation by [12] to choose a number of topics between ten and 50, if the latter interpretation was to be done by humans. The "2 topic distribution" was too generic to label it properly, whereas all topics beyond the "10 topic distribution" did not deliver any new information but rather intermingled previously stable topic compositions.…”

“…In the course of applying the LDA algorithm, normally words are split into single units (one word at a time), while in this context, it is helpful to depict more complex expressions as "digital divide" instead of "digital" and "divide". This option was another recommendation by [12], if the latter interpretation was to be executed by humans, which is the case here. After having set all these preconditions, it was the main task to identify the ideal number of topics.…”

“…This situation resulted from the ever-growing appearance and increased use of web-and cloud-based systems, mobile devices and social media as well as the online storage possibilities of information. New ways of analyzing this massive information like text mining have therefore received growing attention in the last years and have already been successfully applied in research, including the IS discipline [12,17,20,47]. In this respect, this approach represents a powerful tool, because it allows to go beyond the natural boundaries of manual data analyses (quantity-wise), and quasi de facto excludes humanly induced biases (content-wise) [46].…”

“…(1) preparing and uploading the information, (2) deciding on a number of topics and choosing the appropriate pre-processing options and (3) interpreting the details, the suggestions and instructions by [12] were closely followed. According to [12], words that appear in a high frequency can also be set as "stop words", i.e. not considering them within the analysis.…”

Social Collaboration Analytics for Enterprise Collaboration Systems: Providing Business Intelligence on Collaboration Activities

“…Future plans include the application of process mining to ECS (an established concept in business process management [38], [39]) in order to visualize collaboration scenarios [40], [41]. Further, we will try to apply methods from text mining [42] to ECS in order to identify topics of interest.…”