Building mixed-initiative (AI-assisted) tools that collaborate with designers to create interactive narrative scenarios.
Creating a mixed-initiative AI system to evolve new behavior from human-designed behavior trees in Unreal Engine 4.
We present an analysis of the academic landscape of games research from the last 15 years. We employed a data driven approach utilizing co-word and co-venue analysis on 48 core venues to identify 20 major research themes and 7 distinct communities, with a total of 8,207 articles and 21,552 unique keywords being analyzed. The results validated the commonly held assumption that games research has different clusters of papers and venues for technical versus nontechnical research, and identified interactions and synergies between these research clusters.
Using an Role-Playing Game (RPG) with multiple affordances, we designed an experiment collecting granular in-game behaviors of players. Using sequential pattern mining and supervised learning, we developed a model that uses gameplay action sequences to predict the real world characteristics, including gender, game play expertise and five personality traits (as defined by psychology). The results show that game expertise is a dominant factor that impacts in-game behaviors.
In this paper, we consider the problem of skill decomposition in MOBA (MultiPlayer Online Battle Arena) games, with the goal to understand what player skill factors are essential for the outcome of a game match. To understand the construct of MOBA player skills, we utilize various skill-based predictive models to decompose player skills into interpretative parts, the impact of which are assessed in statistical terms. We apply this analysis approach on two widely known MOBAs, namely League of Legends (LoL) and Defense of the Ancients 2 (DOTA2). The finding is that base skills of in-game avatars, base skills of players, and players’ champion-specific skills are three prominent skill components influencing LoL’s match outcomes, while those of DOTA2 are mainly impacted by in-game avatars’ base skills but not much by the other two.
Deck building is a crucial component in playing Collectible Card Games (CCGs). The goal of deck building is to choose a fixed-sized subset of cards from a large card pool, so that they work well together in-game against specific opponents. We propose a deck recommendation system, named Q-DeckRec, which requires small computational resources to recommend winning-effective decks after a training phase thus is suitable for real-time or large-scale application.
Matchmaking connects multiple players to participate in online player-versus-player games. Current matchmaking systems depend on a single core strategy: create fair games at all times. These systems pair similarly skilled players on the assumption that a fair game is best player experience. We demonstrate, however, that this intuitive assumption sometimes fails and that matchmaking based on fairness is not optimal for engagement. Therefore, we propose an Engagement Optimized Matchmaking (EOMM) framework that maximizes overall player engagement. We prove that equal-skill based matchmaking is a special case of EOMM on a highly simplified assumption that rarely holds in reality. Our simulation on real data from a popular game made by Electronic Arts,Inc. (EA) supports our theoretical results, showing significant improvement in enhancing player engagement compared to existing matchmaking methods.
Hero drafting is a challenging problem in MOBA (MultiPlayer Online Battle Arena) games due to the complex hero-to-hero relationships to consider. We propose a novel hero recommendation system that suggests heroes to add to an existing team while maximizing the team’s prospect for victory. To that end, we model the drafting between two teams as a combinatorial game and use Monte Carlo Tree Search (MCTS) for estimating the values of hero combinations. Our empirical evaluation shows that hero teams drafted by our recommendation algorithm have significantly a higher win rate against teams constructed by other baseline and state-of-the-art strategies.
Foldit is a revolutionary crowdsourcing computer game enabling you to contribute to important scientific research by folding proteins in a 3D puzzle game.
Building a system to visualize and identify player as well as team behaviors and strategies.
This project aims to the use a custom-built Alternate Reality Game (ARG) to assess the influence of individual differences on adaptability and teamwork in a digital gaming settings. It has three aims: To develop ARG-based quantitative computational measures that can assess adaptability and performance based on game data, to develop self-report measures that can characterize and measure adaptation processes and behaviours in a mixed-method way, and to validate all behaviour and adaptation measures resulting from this study in the real world.
Description: The project explores the design and development of a 3D puzzle-based game, called May’s Journey, in which players solve an environmental maze by using the game’s pseudo code to manipulate game objects. The game is designed to teach introductory but foundational concepts of computer programming including abstraction, modularity, reusability, and debugging by focusing players […]
Magy Seif El-Nasr
Field: Artificial Intelligence,Game Analytics,Games Research,Evaluation Methodologies for Virtual Environments,Interactive Narratives,Believable Characters,Games and Social Media as Interventions for Health and Learning,Intelligent Adaptive Systems,Virtual Environments
Personal Website: https://web.northeastern.edu/magy/
Google Scholar: https://scholar.google.com/citations?user=SwzKJ0kAAAAJ&hl=en&oi=ao
Short Bio: Magy Seif El-Nasr is an Associate Professor in the Colleges of Computer and Information Sciences and Arts, Media and Design at Northeastern University. Professor Seif El-Nasr directs the PLAIT (Playable Innovative Technologies) Lab. Prior to joining Northeastern, she was an assistant professor at the School of Interactive Arts and Technology at Simon Fraser University (2007-2011). Before that she was an assistant professor at the School of Information Science and Technology at Pennsylvania State University (2003-2007).
Professor Seif El-Nasr believes that problems we currently face in the areas of health, education, resilience, and cybersecurity require an interdisciplinary approach and most often require us to understand human behavior, learning, and human cognition at a deep level which we currently do not possess. Her research focuses on building a framework to facilitate the use of virtual environments (e.g., games, VR, apps, social media or interactive narrative) as a methodology to understand human behavior and cognition, with the goal of facilitating computational solutions to national problems in health, education and security. To address this vision, she develops tools and automated techniques to help author virtual environments (e.g., interactive narratives, believable characters, etc.), as well as data driven analytics to model human behavior in such environments, which can be used to assess as well as personalize the environments towards effective use in solving national problems, such as health and learning.
Professor Seif El-Nasr has chaired and co-chaired several conferences, including PETRA 2013, AIIDE 2013, Foundations of Digital Games (FDG) 2012, International Conference on Entertainment Computing (ICEC) 2011 (Co-Chair), Advances in Computer Entertainment (ACE) 2009 (Program Co-Chair), Computer Human Interaction 2015 (Associate Chair). She also serves on the editorial board of the IEEE Transactions on Computational Intelligence and Game Artificial Intelligence, IEEE Transactions on Affective Computing, Entertainment Computing Journal, and ACM’s Computers in Entertainment. She has also served on several NSF panels throughout her career, and has severed on numerous SIGs, including ACM Representative for TC14 IFIP on Entertainment Computing. In 2017, Dr. Self El-Nasr was selected among 30 game scholars named as fellows for the Higher Education Video Game Association, an association that aims to cultivate a community on game scholarship and education around the world. This was to recognize her leadership role in pioneering and developing games as a field of scholarship and education.
Field: Cognitive Modeling, Decision Making, Sociotechnical Design
Research Projects: OPM; CADE
Google Scholar: https://scholar.google.com/citations?user=mtH2MpMAAAAJ&hl=en
Favorite Game: Cities Skylines
Short Bio: My lifelong research goal is to understand the bidirectional influence of human behavior and technological innovations.
Field: Virtual characters, artificial intelligence, game programming, user and player modeling, HCI
Research Projects: Litmus: Detect Espionage Using Active Indicators; Advancing Methodology for Social Science Research Using Alternate Reality Games;Visualizing Tactics and Strategies through Data from Gallup’s BoomTown Game
Favorite Game: Pacman
Short Bio: I am both a research scientist and a small entrepreneur in the field of interactive software and games. I like addressing problems using an interdisciplinary approach that comes from my background (PhD in Cognitive Science and MSc in General and Experimental Psychology) and research collaborations with institutions in Europe and the US (Department of Computer Science at Carnegie Mellon University, Information Sciences Institute at the University of Southern California, Institute of Education of the University of London, Department of Computer Science of the “Sapienza” University of Rome, Institute of Cognitive Science of the Italian National Research Council, and Nettuno University Consortium in Rome).
Truong-Huy D. Nguyen
Field: Machine learning, Game Analytics, HCI
Research Projects: SSIEGE; DARPA Project on Adaptability
Favorite Game: FIFA18
Short Bio: Truong-Huy D. Nguyen is an assistant professor of computer science at the Department of Computer and Information Science, Fordham University. He is endeavoring to understand human behaviors and decision making, and build experimental and practical applications leveraging such insights.
Field: Reinforcement Learning, Probabilistic Graphical Models, Game Data Visualization
Research Projects: Open Player Modeling, Interactive AI, Explainable AI
Personal Website: https://www.khoury.northeastern.edu/people/zhaoqing-teng/
Favorite Game: Dota2, NBA2K, FIFA, Pokemon
Short Bio: I am interested in building models and programming. Currently I am working on building the cognitive model using probabilistic graphical models like Bayesian networks to reveal the hidden causal relation behind the games.
Field: Game Design/Narrative Design
Research Projects: User Experience in Interactive Narratives, Metagaming and Rewind Mechanics in Interactive Narratives, DARPA, SSEIGE, Litmus
Personal Website: http://erimedia.us
Google Scholar: https://scholar.google.com/citations?user=Q56cKI8AAAAJ&hl=en
Favorite Game: NieR: Automata
Short Bio: I’ve possessed a fascination with games since early childhood that grew into a passion during undergrad. I pursued a Masters in Digital Media and am currently studying Computer Science in order to apply that passion and continue to fuel it through my involvement in various research projects including my own personal work in metagaming and interactive narrative.
Sara BunianPhD Student
Nathan PartlanPhD Student
Chaima JemmaliPhD Student
Josh MillerPhD Student
Sabbir AhmadPhD Student
Abdelrahman MadkourPhD Student
Field: Machine Learning, HCI, Game Analytics, Educational Games
Research Projects: Player Adaptability in Competitive and Collaborative Games
Google Scholar: https://scholar.google.com/scholar?hl=en&as_sdt=0%2C22&q=Sara+Bunian&btnG=
Favorite Game: Crash Bandicoot
Short Bio: Sara’s research interest lies in the intersection between machine learning and game design with the focus on behavioral modeling and creating adaptive educational games. Originally, she come from Kuwait, which is located in the north-east corner of the Arabian Peninsula and had earned her BA And master’s in computer engineering from Kuwait University.
Field: Game AI and Procedural Content Generation
Research Projects: Mixed-Initiative PCG in StudyCrafter (studycrafter.com); Evolving Behavior Trees; Player Imitation Learning
Personal Website: npc.codes
Google Scholar: https://scholar.google.com/citations?user=OkHr9TkAAAAJ
Favorite Game: Caves of Qud
Short Bio: Nathan Partlan, as a Ph.D. student advised by Dr. Magy Seif El-Nasr, is developing practical and designer-focused technologies to expand the possibilities for artificial agents and games. He wants his work to enable people of all backgrounds and abilities to enjoy and become emotionally invested in games of all sorts. Before pursuing a Ph.D., Nathan worked as a professional game programmer, contributing to six shipped commercial titles and three open-source games.
Field: Educational Game Design, Machine Learning
Research Projects: Using Game Design Mechanics as Metaphors to Enhance Learning of Introductory Programming Concepts; Player Adaptability in Competitive and Collaborative Games
Personal Website: https://www.ccis.northeastern.edu/people/chaima-jemmali/
Google Scholar: https://scholar.google.com/citations?user=nsTbf6cAAAAJ&hl=en
Favorite Game: Golden Sun
Short Bio: Interested in balancing learning outcomes and fun in educational games.
Field: Game design, Game-User interaction, Games with a purpose
Research Projects: Foldit
Personal Website: https://www.ccis.northeastern.edu/people/josh-miller/
Favorite Game: Ocarina of Time
Short Bio: Josh’s research focuses on synthesizing game design principles with the psychology of learning and motivation to create seamless and engaging user experiences in non-game contexts. He is interested in creating playful, flow-state experiences for educational contexts. Josh earned his bachelor’s degree in computer science and neuroscience from Colgate University in New York.
Field: Machine Learning, Game Analytics
Research Projects: SSIEGE
Personal Website: https://sites.google.com/site/sabbirahmad010/
Google Scholar: https://scholar.google.com/citations?user=OPrEpHcAAAAJ&hl=en
Favorite Game: Fifa
Short Bio: Sabbir is a PhD student in the Computer Science program at Northeastern University. His research is focused on machine learning and data analytics. Prior to joining Northeastern, he earned his Bachelor’s degree in Computer Science from Bangladesh University of Engineering and Technology.
Field: Player Behavior Modeling
Research Projects: DARPA
Personal Website: https://www.ccis.northeastern.edu/people/abdelrahman-madkour/
Google Scholar: https://scholar.google.com/citations?user=n3rYtFYAAAAJ
Favorite Game: Dark Souls
Short Bio: Madkour is a PhD Student interested in how data of users’ behavior in an interactive environment and/or games can be used to influence and elucidate the experience the user is having. Mostly focusing on understanding and modeling user behavior such that game designers,educators, or other interested parties can glean out what the user is trying to do in a given environment. Prior to joining the GUII Lab Madkour was born and raised in Alexandria Egypt, and earned his BA in Mathematics and Computer Science at St.Olaf College in Northfield Minnesota.
Elin CarstensdottirPhD Student
Zhengxing ChenPhD Student
Dylan G.M SchoutenPostdoctoral researcher
Field: User Experience, Interactive Narrative, Automated Playtesting, Game Design
Research Projects: Interactive Narrative for Social Training
Google Scholar: https://scholar.google.com/citations?user=fO6FFqAAAAAJ&hl=en
Favorite Game: Bloodborne
Short Bio: Elin is a 5th year PhD student researching user experience in interactive narratives. Her interests span a variety of topics centered on how to understand, test, and improve user experience in games, and interactive narratives in particular. Her work is currently focused on automated playtesting and user modeling.
Field: Machine Learning
Research Projects: Engagement Optimized Matchmaking; Hearthstone Deck Recommendation System; Game Avatar Embedding
Personal Website: http://czxttkl.github.io
Google Scholar: https://scholar.google.com/citations?user=LjZLn2MAAAAJ&hl=en
Favorite Game: Counter Strike
Short Bio: Zhengxing Chen is a 5-th year PhD student with his research on personalized recommendation systems in video games. He has broad interests in churn analysis, behavioral clustering, skill modeling, matchmaking and virtual team composition. He has done internships at Electronic Arts, eBay, Google and Facebook where he used AI techniques to improve real-world user engagement problems.
Dylan G.M Schouten
Field: Serious games and Education; HTI; HCI; Design for Education
Research Projects: DARPA ARG Project; Studycrafter (projected)
Personal Website: http://ninja-blues.com/
Google Scholar: https://scholar.google.com/citations?user=DTH3z1sAAAAJ&hl=en
Favorite Game: how can video games be real if our eyes aren’t real
Short Bio: Dutch-born research scientist with a focus on serious games, education, and supporting minority demographics. Currently living in the United States through a series of events and circumstances outside of his own comprehension. Thinks Amsterdam is overrated as a tourist destination. He/him.