Finding the Effectiveness of Software Team Members Using Decision Tree

Abstract

This paper presents steps taken in finding the effectiveness of software team members using decision tree technique. Data sets from software engineering (SE) students were collected to establish pattern relationship among four predictor variables-prior academic achievements, personality types, team personality diversity, and software methodology-as input to determine team effectiveness outcome. There are three main stages involved in this study, which are data collection, data mining using decision tree, and evaluation stage. The results indicate that the decision tree technique is able to predict 69.17 % accuracy. This revealed that the four predictor variables are significant and thus should consider in building a team performance prediction model. Future research will be carried to obtain more data and use a hybrid algorithm to improve the model accuracy. The model could facilitate the educators in developing strategic planning methods in order to improve current curriculum in SE education.

A Strategy Based on Genetic Algorithms for Forming Optimal Collaborative Learning Groups: An Empirical Study

“…Now, from the pedagogical point of view, it is confirming that not considering criteria related to personality traits before the group formation has generally led to lower results. Taking into account personality traits in the group formation process enhances their collaborative performance when it comes to software development activities [78,[82][83][84][85][86][87][88][89][90]. In this aspect, the highlight of the study is that those groups whose formation has been pre-established by the teachers through the proposed strategy, in general, have had a better collaborative performance than groups with traditional formation, except in the case of heterogeneous training.…”

Group formation in collaborative learning contexts based on personality traits: An empirical study in initial Programming courses

“…Specifically, homogeneous grouping presents certain advantages for some types of learning activities, especially those that involve guided discovery, development of skills, review of material that has already been learned, or in highly structured tasks of competencies construction, allowing students to progress at a similar rate, which is beneficial for the achievement of specific goals [1][2][3][4]; this grouping type promotes a positive effect on collaborative learning [5][6][7]. Such is the case of activities that support learning processes in initial programming courses, the context of this study; where, also, considering the personality traits of students in the group formation process enhances their collaborative performance, when it comes to software development activities [8][9][10][11][12][13][14][15][16][17] This paper presents the results of the research process carried out to structure a homogeneous group formation technique in collaborative learning contexts, formation based on personality traits. For this, the "Big Five Inventory" is used as an instrument for measuring the traits of the participants' personality, a standardized inventory or questionnaire based on the psychological model of the Big Five [18].…”