Designing and Evaluating Emotional Student Models for Game-Based Learning

Abstract

Research in game-based learning environments aims to recognise and show emotion. This chapter describes the main approaches and challenges involved in achieving these goals. In addition, we propose an emotional student model that can reason about students' emotions using observable behaviour and responses to questions. Our model uses Control-Value Theory (Pekrun et al. 2007) as a basis for representing behaviour and was designed and evaluated using Probabilistic Relational Models (PRMs), Dynamic Bayesian Networks (DBNs) and Multinomial Logistic Regression. Olympia, a game-based learning architecture, was enhanced to incorporate affect and was used to develop PlayPhysics, an emotional gamebased learning environment for teaching Physics. PlayPhysics' design and emotional student model was evaluated with seventy nine students of Engineering at Tecnológico de Monterrey, Mexico City campus (ITESM-CCM). Results are presented and discussed. Future work will focus on conducting tests with a larger population of students, implementing additional game challenges and incorporating physiological signals to increase the accuracy of classification.

SceneMaker: Creative Technology for Digital StoryTelling

“…The understanding module performs natural language processing, sentiment analysis and text layout analysis of input text utilising algorithms and software from CONFUCIUS [1], NewsViz [20] and 360-MAM-Affect [3]. The reasoning module interprets the context based on common, affective and cinematic knowledge bases, updates emotional states and creates plans for actions, their manners and representation of the set environment with algorithms and software from Control-Value Theory emotion models [2] and CONFUCIUS [1]. StoryTelling techniques developed in [26] will also be employed here and gender and affect in performance [27] will also be important.…”

“…The syntactic knowledge base parses input text and identifies parts of speech, e.g., noun, verb, adjective, with the Connexor Part-of-Speech Tagger [33] and determines the constituents in a sentence, e.g., subject, verb and object, with Functional Dependency Grammars [34]. The semantic knowledge base (WordNet [35] and LCS database [37]) and temporal language relations will be extended by an emotional knowledge base, e.g., WordNetAffect [36], emotion processing with 360-MAM-Affect [3], EmoSenticNet [38] and RapidMiner [39] and Control-Value Theory emotional models [2], and context reasoning with ConceptNet [11] to enable an understanding of the deeper meaning of the context and emotions.…”

The Perspectives of Mathematics Pre-Service Teacher Student Toward the Use of Educational Games in Mathematics Learning

“…Even though educational games can support effective mathematics learning. Through educational games, learning is more fun than traditional methods, it also allows students to enjoy the learning process and increase student interest (Munoz, Kevitt, Lunney, Noguez, & Neri, 2011). The teacher's ability to use game media when the learning process in the classroom must also be considered.…”