Interactive Control and Visualization of Difficulty Inferences from User-Interface Commands

Abstract

Recently, there has been research on inferring user emotions. Like other inference research, it requires an iterative process in which what-if scenarios are played with different features and algorithms. Traditional, general-purpose data mining tools such as Weka have played an important part in promoting this process. We have augmented this toolset with an additional interactive test-bed designed for prediction and communication of programmer difficulties from userinterface commands. It provides end-user interfaces for communicating, correcting, and reacting to the predictions. In addition, it offers researchers user-interfaces for interacting with the prediction process as it is executed rather than, as in traditional mining tools, after it has generated data for a set of experimental subjects. These user-interfaces can be used to determine key elements of the prediction process, why certain wrong or right predictions have been made, and change parameters of the process. A video demonstration this work is available at http://youtu.be/09LpDIPG5h8.

ProLog2vec: Detecting Novices’ Difficulty in Programming Using Deep Learning

“…Thus his study has proved that features only relevant programming itself work well in detection. Compared to Cater's research, Long et al [13], [14] adopted different features from programming logs but also purely based on the logs. After this, Cater in his study [15] manually designed several different features compared to his previous study, though the result seemed to be not very good and the recall rate dropped to 72%.…”

“…In fact, the logging tool should: i)match the IDE, ii)adapt to the granularity of the behaviour data, and iii) extract rich information from events. To choose the most suitable recording tools, we analysed and compared different programming behaviour recording tools(Including the CloudCoder [24], the PCRS [25], the TestMyCode [26], the Blackbox [27], the Mckeogh [28], the Eclipseye [29], and the Eclipse-Helper [13]) from aspects of programming language, IDE support, and data type of records. The FLUORITE, developed by Yoon et al [30] was chosen for the abundant recorded information, applicability of the client, and convenience of deploy and modification.…”