Manuel Freire

Serious games have several advantages for learning over more traditional activities. One of those advantages is that being highly interactive, they provide a firsthand simulated experience to the users. Serious games can also generate interaction data that can be used to assess learning, both for evaluation and to provide timely feedback for learners or even adapt aspects of the game on the fly. However, this potential is currently far from realized because doing so requires significant investment and expertise as compared to more traditional educational activities. Additionally, game learning analytics continue to be a costly and fragile process. We propose a combination of tools that greatly reduces the associated costs of building serious games with meaningful analytics simplifying the validation of those games and their deployment in real settings. We consider that this can be a key step to building predictive assessment avoiding the need for disruptive external assessment thus bootstrapping serious games to recognize learning through analytics.

Game learning analytics (GLA) comprise the collection, analysis, and visualization of player interactions with serious games. The information gathered from these analytics can help us improve serious games and better understand player actions and strategies, as well as improve player assessment. However, the application of analytics is a complex and costly process that is not yet generalized in serious games. Using a standard data format to collect player interactions is essential: the standardization allows us to simplify and systematize every step in developing tools and processes compatible with multiple games. In this paper, we explore a combination of 1) an exploratory visualization tool that analyzes player interactions in the game and provides an overview of their actions, and 2) an assessment approach, based on the collection of interaction data for player assessment. We describe some of the different opportunities offered by analytics in game-based learning, the relevance of systematizing the process by using standards and game-independent analyses and visualizations, and the different techniques (visualizations, data mining models) that can be applied to yield meaningful information to better understand learners’ actions and results in serious games.

Bioelectric signals can improve assessment in videogames by helping to better understand user experience, evaluate attention, or study the cognitive and physical effects of games. Use of signals is therefore relevant to better evaluate and understand the impact and effects of videogames on players, and specially so in the field of serious games, such as educational or training games, to gain insights into the learning processes; or in games for health to better evaluate non-conscious effects on the player’s body. We examine how biological signals (bioelectric + eye-tracking) are being used and collected in the field of video games, including the choice of signals, the devices used to collect them (e.g., wearables), the purposes for which they are collected, and the results reported from their use. As a result of this systematic literature review, 81 articles have been analyzed, finding that electrocardiograms and encephalograms are the most frequently used signals. The main use of these bioelectrical signals is to evaluate player engagement, level of difficulty, and stress during the gameplay. But there are also examples where signals are used to detect health problems, or as evidence to compare educational games with other learning activities. This review informs researchers interested in better understanding the benefits and limitations of biological signals for video games, providing an overview of studies conducted in recent years and the associated devices described in those studies. Limitations in this field include signal noise issues as well as the amount of time required to calibrate the devices during experiments, adding to the complexity of user testing. It is necessary to work on tools that facilitate experiments with large groups of users in parallel as well as to work on open software and low-cost devices that allow the emergence of a greater number of studies in this field, given for example their potential in the field of educational games to better understand the learning processes of users.

Game Learning Analytics can be used to conduct evidence-based evaluations of the effect that serious games produce on their players by combining in-game user interactions and traditional evaluation methods. We illustrate this approach with a case-study where we conduct an evidence-based evaluation of a serious game’s effectiveness to increase awareness of bullying. In this paper, we describe: (1) the full process of tracking in-game interactions, analyzing the traces collected using the standard xAPI-SG format, and deriving game learning analytics variables (to be used as evidences); and (2) the use of those variables to predict the increase in bullying awareness. We consider that this process can be generalized and replicated to systematize, and therefore simplify, evidence-based evaluations for other serious games based on the interaction data of their players.

Serious games’ evaluation and players’ assessment is commonly done with experiments where the users play the game and fulfill one or more questionnaires. The tool Simva was designed to simplify these complex experiments, which commonly include the collection of game learning analytics data to provide further insight about players’ progress and results. We present the latest updates on the tool Simva and three applications where it was used to validate serious games using pre-post experiments and collecting game learning analytics data of players’ in-game interactions.