Integrating Data Mining and Social Network Techniques into the Development of a Web-based Adaptive Play-based Assessment tool for School Readiness.

摘要

A major challenge that faces most families is effectively anticipating how ready toudstart school a given child is. Traditional tests are not very effective as they depend onudthe skills of the expert conducting the test. It is argued that automated tools are moreudattractive especially when they are extended with games capabilities that would beudthe most attractive for the children to be seriously involved in the test. The first partudof this thesis reviews the school readiness approaches applied in various countries.udThis motivated the development of the sophisticated system described in the thesis.udExtensive research was conducted to enrich the system with features that considerudmachine learning and social network aspects. A modified genetic algorithm wasudintegrated into a web-based stealth assessment tool for school readiness. Theudresearch goal is to create a web-based stealth assessment tool that can learn the user'sudskills and adjust the assessment tests accordingly. The user plays various sessionsudfrom various games, while the Genetic Algorithm (GA) selects the upcoming sessionudor group of sessions to be presented to the user according to his/her skills and status.udThe modified GA and the learning procedure were described. A penalizing systemudand a fitness heuristic for best choice selection were integrated into the GA. Twoudmethods for learning were presented, namely a memory system and a no-memoryudsystem. Several methods were presented for the improvement of the speed ofudlearning. In addition, learning mechanisms were introduced in the social networkudaspect to address further usage of stealth assessment automation. The effect of theudrelatives and friends on the readiness of the child was studied by investigating theudsocial communities to which the child belongs and how the trend in theseudcommunities will reflect on to the child under investigation.udThe plan is to develop this framework further by incorporating more informationudrelated to social network construction and analysis. Also, it is planned to turn theudframework into a self adaptive one by utilizing the feedback from the usage patternsudto learn and adjust the evaluation process accordingly.