There is a global shortage of therapeutic, educational, and social support for neurodivergent children and youth, with substantial downstream consequences for individual well-being and societal costs in adulthood. While early and sustained support is known to be both humane and economically effective, existing service models struggle to scale. Therapeutically Assisted Role-Playing Games (TARPGs) have recently emerged as a promising, group-based intervention that combines guided play, narrative structure, and social skill rehearsal to support neurodivergent development. Case studies consistently report positive outcomes, including increased engagement, social connection, emotional regulation, and self-efficacy. However, current research remains dominated by small-scale and non-experimental case studies, and practical barriers persist for wider adoption, especially for carers without formal therapeutic training. Therapists are often not available, and carers are the next, and more numerous, line of support for neurodivergent children. This paper introduces AURA (AI-Assisted Understanding of Role-play), a novel system designed to support therapists and carers running TARPG sessions. AURA addresses a key practical challenge in TARPG facilitation: documenting complex, multi-player narrative sessions without disrupting live interaction. By analysing audio and/or video recordings of sessions, AURA generates structured post-session summaries, and key event timeline, enabling facilitators to focus on participants rather than note-taking. AURA aims to lower barriers to entry, extend TARPG capacity beyond scarce clinical settings, and support more scalable, evidence-informed interventions for neurodivergent children and youth.

This paper explores the application of bandit methods for the assignment of “starter packs” to new players in a free-to-play mobile game environment. Leveraging an online reinforcement learning system, the study aims to strategically assign starter packs to players from different country and device segments. The architecture of the online experimentation system enables real-time decision-making processes and continuous model tuning. The cold start problem is addressed by seeding the bandit with a prior offer policy informed by institutional expertise. Offline evaluation on a dataset derived from a previous AB test conducted by the company and two online experiments assess the abilities of bandit methods to assign starter packs to new players in this environment. While personalization of starter pack assignment in contextual data (country and device segments) is not achieved, a bandit with a conversion-reward changes the prior institutional policy and lowers the average effective sales price of starter packs to new players. The bandit’s policy achieves an indicative lift in per-user revenue, repeat purchasing, and player retention compared to a holdout group with a naive policy. This research contributes to the field of monetization strategies in mobile free-to-play games, emphasizing the design of systems for online personalization and revenue optimization.

Games are frequently viewed as spatial constructs, where the game space enables play, creates challenge, and enhances and facilitates immersion. The spatial analysis of player behavior thus constitutes a key element in games user research and game analytics to help understand how players navigate game environments. However, the complexity of movement calls for visual solutions that clearly define and communicate patterns in player behavior. In this paper, we address this challenge by introducing a method for visualizing aggregated player trajectories, also in conjunction with other behavioral metrics. This way movement is not viewed in isolation but contextualized within the broader player behavior. Line integral convolution textures are used to summarize the structural patterns of the movement while additional data can be displayed simultaneously through encoding it in the visual channels of the texture. Further, α -shapes are used to highlight and describe the spatial shape of the traversed parts of the game environment. We demonstrate the approach by applying it to the popular esports games Dota 2 and Starcraft: Brood War and discuss its generalizability within and outside esports.

Esports has become a popular field of research, enabling advances in areas such as machine learning and environment modeling. However, complex modeling systems require complex visualisations. Despite that, visualisation of complex modeling systems within esports have been limited or fragmented, particularly when focused on the audience. Furthermore, the use of data visualisation and data-driven storytelling has been proven to be an effective and imperative method for enhancing audience experience for esport spectators. Therefore, this paper investigates data visualisation techniques within esports, and compiles design considerations for developing visualisation tools for esports broadcast. This is achieved through a case-study, in which the WARDS model was utilised in live coverage of a Dota 2 tournament and evaluated through observational data.

Esports - competitive video games watched by online audiences - are the fastest growing form of mainstream entertainment. Esports coverage is predominantly delivered via online video streaming platforms which include interactive elements. However, there is limited understanding of how audiences engage with such interactive content. This paper presents a large-scale case study of an interactive data-driven streaming extension developed for Dota 2, reaching over 300,000 people during the DreamLeague Season 15 DPC Western Europe tournament. The extension provides interactive live statistics, analysis and highlights reels of ongoing matches. This paper presents an analysis of audience telemetry collected over the course of the four week tournament, introducing a novel approach to analysing usage data delivered seamlessly in conjunction to a linear broadcast feed. The work presented advances our general understanding of the evolving consumption patterns in esports, and leverages esports as a lens to understand future challenges and opportunities in interactive viewing across sports and entertainment.

Data analytics is commonly used to enable storytelling and enhance esport coverage. One prominent use of it is win prediction, where machine learning models predict the winner of the game before its conclusion. However, predictions are most commonly results of black-box systems, forcing commentators to produce ad-hoc interpretations. Additionally, broadcasters generally rely other metrics to build narratives, limiting the impact of win prediction models for storytelling. This paper explores an alternative method to win prediction, identifying the needs of broadcasters to guide development of a novel win condition model. By focusing on existing storytelling points, the proposed win condition model can offer greater storytelling opportunities to broadcasters, focusing on the user needs identified from within the esport domain. Rather than utilising game state data to predict the winner, as it is usually done in win prediction, the proposed win condition model uses an exploration of the possible winners to predict the game state needed for each team to win. Lastly, the features identified for win condition are evaluated through a series of machine learning models, which provide a data-driven metric to test and predict win condition in the context of Dota 2, a popular esport title.

Esports - games played competitively - comprise a major sector of the global games industry. Esports has been used as a testbed for game AI and game analytics for two decades. This article presents a multivocal literature mapping of available research that focuses strictly on the use of artificial intelligence approaches in Multiplayer Online Battle Arena (MOBA) games, one of the most popular esports genres and the one most widely used for game AI and game analytics research. A mapping is performed on relevant publications published between 2011 and 2022 and systematically examines them to extract similarities, gaps, and main findings. We analyzed 124 publications to identify the most studied topics, the most commonly used techniques, and the most commonly applied evaluation methods. The results show that League of Legends and DOTA are the most studied games, with outcome prediction being the most popular research topic. Finally, we provide an analysis of the potential future flagship areas for research in the domain, considering the gaps found in the white and grey literature.

Esports are complex computer games that are played competitively. DOTA 2 is one of the most popular esports titles worldwide. Commentators, audiences, and players face tremendous challenges to keep up with events happening during live matches due to a rapidly evolving gameplay across a large virtual arena. This complexity leads to the question of whether esports analytics could detect important events and their subsequent impact on the match. One such important event is team fights, which can often determine the outcome of a match. Despite their significance across strategy, gameplay, and audience experience, team fights remain relatively unexplored in the literature. Their role and potential to support match prediction models are not well understood. This paper presents a novel definition of team fights in DOTA 2 and proposes an algorithm to extract and quantity them for use in match prediction.

Thousands of technology professionals attend in-person meetups each month in cities around the world. However, during the Covid-19 pandemic, social distancing requirements have forced meetups in many locations to operate exclusively virtual events for the first time. We surveyed participants (n=251) who attend technology meetup communities in the UK to find out how the pivot from in-person to virtual meetings has affected meetup communities. We gathered data about participants' experiences of virtual meetups and compared with in-person experiences. While in-person meetups are important venues for practitioners to network, learn, socialise, meet people and participate in discussions (enabling transfer of tacit knowledge), participants attend virtual meetings primarily for learning. Virtual meetups offer poor support for socialising, networking, discussion and transfer of tacit knowledge, However, they do offer learning opportunities via structured talks and content, and can rival in-person meetups when it comes to learning new skills like programming, keeping up to date with general technology developments and improving one's general practice. The low barrier to entry for virtual events improves accessibility for both speakers and participants. Our findings suggest that some meetups may benefit from considering how to incorporate virtual meeting formats into their schedules for the long-term.

Team cohesion is a widely known predictor of performance and collaborative satisfaction. However, how it develops and can be assessed, especially in fast-paced ad hoc dynamic teams, remains unclear. An unobtrusive and objective behavioural measure of cohesion would help identify determinants of cohesion in these teams. We investigated team communication as a potential measure in a mixed-methods study with 48 teams (n=135) in the digital game League of Legends. We first established that cohesion shows similar performance and satisfaction in League of Legends. teams as in non-game teams and confirmed a positive relationship between communication word frequency and cohesion. Further, we conducted an in-depth exploratory qualitative analysis of the communication sequences in a high-cohesion and a low-cohesion team. High cohesion is associated with sequences of apology->encouragement, suggestion->agree/acknowledge, answer->answer, and answer->question, while low-cohesion is associated with sequences of opinion/analysis->opinion/analysis, disagree->disagree, command->disagree, and frustration->frustration. Our findings also show that cohesion is important to team satisfaction independently of the match outcomes. We highlight that communication sequences are more useful than frequencies to determine team cohesion via player interactions.

Esport is a large and still growing industry with vast audiences. Multiplayer Online Battle Arenas (MOBAs), a sub-genre of esports, possess a very complex environment, which often leads to experts missing important coverage while broadcasting live competitions. One common game event that holds significant importance for broadcasting is referred to as a team fight engagement. Professional player's own knowledge and understanding of the game may provide a solution to this problem. This paper suggests a model that predicts and detects ongoing team fights in a live scenario. This approach outlines a novel technique of deriving representations of a complex game environment by relying on player knowledge. This is done by analysing the positions of the in-game characters and their associated cameras, utilising this data to train a neural network. The proposed model is able to both assist in the production of live esport coverage as well as provide a live, expert-derived, analysis of the game without the need of relying on outside sources.

Work in AI-based explanation systems has uncovered an interesting contradiction: people prefer and learn best from why explanations but expert esports commentators primarily answer what questions when explaining complex behavior in real-time strategy games. Three possible explanations for this contradiction are: 1.) broadcast audiences are well-informed and do not need why explanations; 2.) consuming why explanations in real-time is too cognitively demanding for audiences; or 3.) producing live why explanations is too difficult for commentators. We answer this open question by investigating the effects of explanation types and presentation modalities on audience recall and cognitive load in the context of an esports broadcast. We recruit 111 Dota 2 players and split them into three groups: the first group views a Dota 2 broadcast, the second group has the addition of an interactive map that provides what explanations, and the final group receives the interactive map with detailed why explanations. We find that participants who receive short interactive text prompts that provide what explanations outperform the no explanation group on a multiple-choice recall task. We also find that participants who receive detailed why explanations submit reports of cognitive load that are higher than the no explanation group. Our evidence supports the conclusion that informed audiences benefit from explanations but do not have the cognitive resources to process why answers in real-time. It also supports the conclusion that stacked explanation interventions across different modalities, like audio, interactivity, and text, can aid real-time comprehension when attention resources are limited. Together, our results indicate that interactive multimedia interfaces can be leveraged to quickly guide attention and provide low-cost explanations to improve intelligibility when time is too scarce for cognitively demanding why explanations.

Esports are competitive videogames watched by audiences. Most esports generate detailed data for each match that are publicly available. Esports analytics research is focused on predicting match outcomes. Previous research has emphasized prematch prediction and used data from amateur games, which are more easily available than those from professional level. However, the commercial value of win prediction exists at the professional level. Furthermore, predicting real-time data is unexplored, as is its potential for informing audiences. Here, we present the first comprehensive case study on live win prediction in a professional esport. We provide a literature review for win prediction in a multiplayer online battle arena (MOBA) esport. This article evaluates the first professional-level prediction models for live DotA 2 matches, one of the most popular MOBA games, and trials it at a major international esports tournament. Using standard machine learning models, feature engineering and optimization, our model is up to 85% accurate after 5 min of gameplay. Our analyses highlight the need for algorithm evaluation and optimization. Finally, we present implications for the esports/game analytics domains, describe commercial opportunities and practical challenges, and propose a set of evaluation criteria for research on esports win prediction.

In social and online media, influencers have traditionally been understood as highly visible individuals. Recent outcomes suggest that people are likely to mimic influencers’ behavior, which can be exploited, for instance, in marketing strategies. Also in the Games User Research field, the interest in studying player social networks has emerged due to the heavy reliance on online influencers in marketing campaigns for games, as well as in keeping players engaged. Despite the inherent value of those individuals, it is still difficult to identify influencers, as the definition of influencers is a debated topic. Thus, how can we identify influencers, and are they indeed the individuals impacting others’ behavior? In this work, we focus on influence in retention to verify whether central players impacted others’ permanence in the game. We identified the central players in the social network built from the competitive player-vs-player (PvP) multiplayer (Crucible) matches in the online shooter Destiny. Then, we computed influence scores for each player evaluating the increase in similarity over time between two connected individuals. In this paper, we were able to show the first indications that the traditional metrics for influencers do not necessarily apply for games. On the contrary, we found that the group of central players was distinct from the group of influential players, defined as the individuals with the highest influence scores. Then, we provide an analysis of the two groups.

Informal technology 'meetups' have become an important aspect of the software development community, engaging many thousands of practitioners on a regular basis. However, although local technology meetups are well-attended by developers, little is known about their motivations for participating, the type or usefulness of information that they acquire, and how local meetups might differ from and complement other available communication channels for software engineering information. We interviewed the leaders of technology-oriented Meetup groups, and collected quantitative information via a survey distributed to participants in technology-oriented groups. Our findings suggest that participants in these groups are primarily experienced software practitioners, who use Meetup for staying abreast of new developments, building local networks and achieving transfer of rich tacit knowledge with peers to improve their practice. We also suggest that face to face meetings are useful forums for exchanging tacit knowledge and contextual information needed for software engineering practice.

Esports (competitive videogames) have grown into a global phenomenon with over 450m viewers and a 1.5bn USD market. Esports broadcasts follow a similar structure to traditional sports. However, due to their virtual nature, a large and detailed amount data is available about in-game actions not currently accessible in traditional sport. This provides an opportunity to incorporate novel insights about complex aspects of gameplay into the audience experience – enabling more in-depth coverage for experienced viewers, and increased accessibility for newcomers. Previous research has only explored a limited range of ways data could be incorporated into esports viewing (e.g. data visualizations post-match) and only a few studies have investigated how the presentation of statistics impacts spectators’ experiences and viewing behaviors. We present Weavr, a companion app that allows audiences to consume data-driven insights during and around esports broadcasts. We report on deployments at two major tournaments, that provide ecologically valid findings about how the app’s features were experienced by audiences and their impact on viewing behavior. We discuss implications for the design of second-screen apps for live esports events, and for traditional sports as similar data becomes available for them via improved tracking technologies.

In a wide range of social networks, people's behavior is influenced by social contagion: we do what our network does. Networks often feature particularly influential individuals, commonly called "influencers." Existing work suggests that in-game social networks in online games are similar to real-life social networks in many respects. However, we do not know whether there are in-game equivalents to influencers. We therefore applied standard social network features used to identify influencers to the online multiplayer shooter Tom Clancy's The Division. Results show that network feature-defined influencers had indeed an outsized impact on playtime and social play of players joining their in-game network.

Data-driven approaches which aim to identify and predict player engagement are becoming increasingly popular in games industry contexts. This is due to the growing practice of tracking and storing large volumes of in-game telemetries coupled with a desire to tailor the gaming experience to the end-user's needs. These approaches are particularly useful not just for companies adopting Game-as-a-Service (GaaS) models (e.g. for re-engagement strategies) but also for those working under persistent content-delivery regimes (e.g. for better audience targeting). A major challenge for the latter is to build engagement models of the user which are data-efficient, holistic and can generalize across multiple game titles and genres with minimal adjustments.This work leverages a theoretical framework rooted in engagement and behavioural science research for building a model able to estimate engagement-related behaviours employing only a minimal set of game-agnostic metrics. Through a series of experiments we show how, by modelling early user-game interactions, this approach can make joint estimates of long-term survival time and churn probability across several single-player games in a range of genres. The model proposed is very suitable for industry applications since it relies on a minimal set of metrics and observations, scales well with the number of users and is explicitly designed to work across a diverse range of titles.

Esports have become major international sports with hundreds of millions of spectators. Esports games generate massive amounts of telemetry data. Using these to predict the outcome of esports matches has received considerable attention, but micro-predictions, which seek to predict events inside a match, is as yet unknown territory. Micro-predictions are however of perennial interest across esports commentators and audience, because they provide the ability to observe events that might otherwise be missed: esports games are highly complex with fast-moving action where the balance of a game can change in the span of seconds, and where events can happen in multiple areas of the playing field at the same time. Such events can happen rapidly, and it is easy for commentators and viewers alike to miss an event and only observe the following impact of events. In Dota 2, a player hero being killed by the opposing team is a key event of interest to commentators and audience. We present a deep learning network with shared weights which provides accurate death predictions within a five-second window. The network is trained on a vast selection of Dota 2 gameplay features and professional/semi-professional level match dataset. Even though death events are rare within a game (1% of the data), the model achieves 0.377 precision with 0.725 recall on test data when prompted to predict which of any of the 10 players of either team will die within 5 seconds. An example of the system applied to a Dota 2 match is presented. This model enables real-time micro-predictions of kills in Dota 2, one of the most played esports titles in the world, giving commentators and viewers time to move their attention to these key events.

Social media has become a major communication channel for communities centered around video games. Consequently, social media offers a rich data source to study online communities and the discussions evolving around games. Towards this end, we explore a large-scale dataset consisting of over 1 million tweets related to the online multiplayer shooter Destiny and spanning a time period of about 14 months using unsupervised clustering and topic modelling. Furthermore, we correlate Twitter activity of over 3,000 players with their playtime. Our results contribute to the understanding of online player communities by identifying distinct player groups with respect to their Twitter characteristics, describing subgroups within the Destiny community, and uncovering broad topics of community interest.

Behavioral profiling of players in digital games is a key challenge in game analytics, representing a particular challenge in Open-World Games. These games are characterized by large virtual worlds and few restrictions on player affordances. In these games, incorporating the spatial and temporal dimensions of player behavior is necessary when profiling behavior, as these dimensions are important to the playing experience. We present analyses that apply cluster analysis and the DEDICOM decompositional model to profile the behavior of more than 5,000 players of the major commercial title Just Cause 2 integrating both spatio-temporal trails and behavioral metrics. The application of DEDICOM to profile the spatio-temporal behavior of players is demonstrated for the purpose of analysing the entire play history of Just Cause 2 players, but also for the more detailed analysis of a single mission. This showcases the applicability of spatio-temporal profiling to condense player behavior across large sample sizes, across different scales of investigation. The method presented here provides a means to build profiles of player activity in game environments with high degrees of freedom across different scales of analysis - from a small segment to the entire game.

Social features, matchmaking, and grouping functions are key elements of online multiplayer experiences. Understanding how social connections form in and around games and their relationship to in-game activity offers insights for building and maintaining player bases and for improving engagement and retention. This paper presents an analysis of the groups formed by users of the the 100.io-a social matchmaking website for different commercial titles, including Destiny on which we focus in this paper. Groups formed on the 100.io can be described across a range of social network related metrics. Also, the social network formed within a group is evaluated in combination with user-provided demographic and preference data. Archetypal analysis is used to classify groups into archetypes and a correlation analysis is presented covering the effect of group characteristics on in-game activity. Finally, weekly activity profiles are described. Our results indicate that group size as well as the number of moderators within a group and their connectedness to other team members influences a group's activity. We also identified four prototypical types of groups with different characteristics concerning composition, social cohesion, and activity.

In recent years, microblogging platforms have not only become an important communication channel for the game industry to generate and uphold audience interest but also a rich resource for gauging player opinion. In this paper we use data gathered from Twitter to examine which topics matter to players and to identify influential members of a game's community. By triangulating in-game data with Twitter activity we explore how tweets can provide contextual information for understanding fluctuations in in-game activity. To facilitate analysis of the data we introduce a visual data exploration tool and use it to analyze tweets related to the game Destiny. In total, we collected over one million tweets from about 250,000 users over a 14-month period and gameplay data from roughly 3,500 players over a six-month period.

This paper examines in-real-life (irl) sport and eSports in an attempt to clarify the definition of eSport. The notion of physicality and embodiment are central to the need for clarity in understanding of what eSports are and whether they are sport or some other activity. By examining existing definitions of eSport and irlSport we can identify the similarities and differences between these activities. Methodologically the paper uses the philosophical process of critical thinking and analysis to examine the various approaches taken to defining both eSport and irlSports. Our aim is to highlight the inherent problem of the definition of eSports and irlSports (and the privileging of the term sport as it currently applies only to irlSports). We find that eSports are sports and that the definition of sport should be expanded to include sub-categories of irlSports and eSports.

Recent years have seen a deluge of behavioral data from players hitting the game industry. Reasons for this data surge are many and include the introduction of new business models, technical innovations, the popularity of online games, and the increasing persistence of games. Irrespective of the causes, the proliferation of behavioral data poses the problem of how to derive insights therefrom. Behavioral data sets can be large, time-dependent and high-dimensional. Clustering offers a way to explore such data and to discover patterns that can reduce the overall complexity of the data. Clustering and other techniques for player profiling and play style analysis have, therefore, become popular in the nascent field of game analytics. However, the proper use of clustering techniques requires expertise and an understanding of games is essential to evaluate results. With this paper, we address game data scientists and present a review and tutorial focusing on the application of clustering techniques to mine behavioral game data. Several algorithms are reviewed and examples of their application shown. Key topics such as feature normalization are discussed and open problems in the context of game analytics are pointed out.

The articles in this special section ddress various flavors of the diverse field of game analytics. It covers topics ranging from player profiling, behavioral prediction, metrics extraction from gameplay recordings, behavioral analysis, retention analysis, and more.

Frustration, in small, calibrated doses, can be integral to an enjoyable game experience, but it is a very delicate balance: just a slightly excessive amount of frustration could compel players to terminate prematurely the experience. Another factor with high relevance when analyzing player frustration is the difference in personality between players: some are less willing to endure frustration and might give up on the game earlier than others. This article seeks to identify patterns of behavior that could point to potential frustration before players resolve to quit a game. The method should be applicable independently from the personalities of different players. Furthermore, in order for this method to be relevant during game production, it has been decided to avoid relying on large numbers of players, and instead depend on highly granular data and both qualitative approaches (direct observation of players) and quantitative research (data mining gameplay metrics). The result is a computational model of player frustration that, although applied to a single game (Kane & Lynch 2), is able to raise a red flag whenever a sequence of actions in the game could be interpreted as possible player frustration.

The practice of illegally copying and distributing digital games is at the heart of one of the most heated and divisive debates in the international games environment, with stakeholders typically viewing it as a very positive (pirates) or very negative (the industry, policy makers). Despite the substantial interest in game piracy, there is very little objective information available about its magnitude or its distribution across game titles and game genres. This paper presents a large-scale analysis of the illegal distribution of digital game titles, which was conducted by monitoring the BitTorrent peer-to-peer (P2P) file-sharing protocol. The sample includes 173 games and a collection period of three months from late 2010 to early 2011. A total of 12.6 million unique peers were identified, making this the largest examination of game piracy via P2P networks to date. The ten most pirated titles encompass 5.27 million aggregated unique peers alone. In addition to genre, review scores were found to be positively correlated with the logarithm of the number of unique peers per game (p<0.05).