JOURNAL OF L A T E X CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 A Fuzzy Control System for Inductive Video Games Carlos Lara- ´ Alvarez,Hugo Mitre-Hern ´ andez,Juan J Flores, and Maria Fuentes, Abstract—It has been shown that the emotional state of students has an important relationship with learning; for instance, engaged concentration is positively correlated with learning. This paper proposes the Inductive Control (IC) for educational games. Unlike conventional approaches that only modify the game level, the proposed technique also induces emotions in the player for supporting the learning process. This paper explores a fuzzy system that analyzes the players’ performance and their emotional state for controlling the level and aesthetic content of an educational video game. The emotional state of the player is recognized through voice analysis. A total of 20 subjects played a video game designed to practice basic math skills; for each trial, a student plays two times in a row the same game but each time the game was controlled by one of the two approaches —Dynamic Difficulty Adjustment (DDA) and IC, the playing order was assigned randomly. Results show that when the proposed approach is used the participants changed faster from Unpleasant–low to pleasant or high emotions, and reached softly and kept in the flow zone. These experiments demonstrate that the inductive control technique improves the learning effectiveness through detection and stimulation of positive emotions. Index Terms—Fuzzy control, Affective computing, Interactive learning control ✦ 1 I NTRODUCTION A N educational video game is a computer game that induces user engagement while promoting cognitive learning and social skills. Several authors have suggested the potential of video and computer games as educational tools [1]; for example, Rosas et al. [2] show that learning through video games has positive effects for children in the first years of school. Indeed, under certain conditions, edu- cational games are preferable over other teaching method- ologies Peterson [3]. In general, a successful educational game requires that its mechanics (game components), dynamics (behavior as responses of the players inputs) and aesthetics (environment shapes, animations, sound, etc.) fulfill the expectations of the target population. Each player has specific character- istics –e.g. preferences, abilities, emotions–, therefore, the game must change its dynamics and aesthetics. Adaptive Game Adjustment (AGA) is a common approach to optimize output performance measures of the game (e.g., the player’s experience). The AGA methods can be divided into two general classes [4]: Dynamic Difficulty Adjustment (DDA). these methods (aka dynamic game balancing) automatically change parameters, scenarios, and behaviors in a video game in real-time, based on the player’s ability. In the context of serious games, these methods use the Zone of Proximal Development theory (ZPD) [5]. In his theory, Vygotsky considers two development levels for learners: the actual development level –what a learner can do on her own– and the potential development level • C. Lara is CONACYT Research Fellow commissioned to CIMAT, Zacate- cas, Mexico, 98000. E-mail: carlos.lara@cimat.mx • H. Mitre is with Center for Research in Mathematics, AC (CIMAT). Zacatecas, Mexico, 98000 • J. Flores is with Michoacana University, Morelia, Michoacan, Mexico. Manuscript received April 19, 2005; revised August 26, 2015. –what a learner can perform with some assistance–. Vygotsky defines the ZPD as: “The distance between the actual development level as determined by independent problem solv- ing and the level of potential development as determined through problem solving under adult guidance or collaboration of more capable peers”. A simple interpretation of the ZPD theory is that the instructional material should not be too difficult or easy for the learner [6]. This approach argues that by keeping learners in their ZPD, negative emotional extremes can be prevented – e.g., being bored, confused or frustrated [6]. Likewise, the Flow theory [7, 8, 9] describes different mental states that can be induced in a learner by a combination of skill and challenge levels. The ‘flow experience’ model marks an achieved balance of arousal-increasing and arousal-decreasing processes. The flow model describes this balance in terms of the fit between perceived challenges and skills: an activity wherein challenges predominate increases arousal; an activity wherein skills predominate reduces arousal. Thus, a synchrony of challenges and skills permits a state of deep involvement, while the pitfalls of either over- or under-arousal (i.e., anxiety or boredom) are avoided. Emotionally Adaptive (EA) Methods. These methods con- sider that by maintaining a high level of engagement, the game experience could lead to psychological ben- efits, such as a sense of efficacy and power over one’s environment, as well as improvements in learning [10]. The Affective Loop [11, 12] states that: by providing the right game content the game influences the player’s experience, and by detecting the emotional state of the player the game can adapt its content. Anxiety and boredom emotions have a negative effect arXiv:1709.00927v1 [cs.HC] 4 Sep 2017