This paper demonstrated how to apply Machine Learning (ML) techniques to analyze student interaction data collected in an online mathematics game. Using a data-driven approach, we examined 1) how different ML algorithms influenced the precision of middle-school students' (N = 359) performance (i.e. posttest math knowledge scores) prediction and 2)…

This paper demonstrated how to apply Machine Learning (ML) techniques to analyze student interaction data collected in an online mathematics game. Using a data-driven approach, we examined: (1) how different ML algorithms influenced the precision of middle-school students' (N = 359) performance (i.e. posttest math knowledge scores) prediction; and…

This paper demonstrates how to apply Machine Learning (ML) techniques to analyze student interaction data collected in an online mathematics game. We examined: (1) how different ML algorithms influenced the precision of middle-school students' (N = 359) performance prediction; and (2) what types of in-game features were associated with student…

This study proposes a new method named the IIS-map-based method for analyzing interactions in face-to-face collaborative learning settings. This analysis method is conducted in three steps: firstly, drawing an initial IIS-map according to collaborative tasks; secondly, coding and segmenting information flows into information items of IIS; thirdly,…

Responds to a paper by Brant Burleson and continues the dispute regarding whether argument-as-product or argument-as-interaction should be regarded as the paradigm case or exemplar of argument. Defends the primacy of the interactional view by reference to the shortcomings of the serial predicative view. (JMF)

This report presents an analysis of an expert performing a highly interactive computer task. The analysis uses GOMS models, specifying the Goals, Operators, Methods, and Selection rules used by the expert; the GOMS models are implemented within a unified theory of cognition called Soar. Two models are presented, one with function-level operators,…

Researchers are now attempting to improve techniques for studying stable behavior patterns in family systems over long periods of time, e.g., the marital dyad across several levels of function and dysfunction covering time periods of months to years. One approach to improving this research design is based on the assumptions that longitudinal…

The effectiveness of the Delphi Technique is evaluated in terms of immediate and delayed controlled information feedback (feedback within 5 seconds as compared with a 24-hour delay); and the relationships that exist among measures of integrative complexity, estimations about the time of occurrence of future events, and time delay between task…