What We Talk About When We Talk About Games: Bottom-Up Game Studies Using Natural Language Processing (original) (raw)

Natural Language Processing for Games Studies Research

Journal of Simulation & Gaming (S&G), Special Issue on Games Research Methods, 2011

Natural Language Processing in Game Studies Research: An Overview

Simulation & Gaming, 2012

Natural language processing (NLP) is a field of computer science and linguistics devoted to creating computer systems that use human (natural) language as input and/or output. We propose that NLP can also be used for game studies research. In this article we provide an overview of NLP and describe a few research possibilities that can be explored using its tools and techniques. We discuss these techniques by performing three different types of NLP analyses of a significant corpus of online videogame reviews. First, using techniques such as word and syllable counting, we analyze the readability of professionally written game reviews finding that, across a variety of indicators, game reviews are written for a secondary education reading level. Next, we analyze hundreds of thousands of user-submitted game reviews using part-of-speech tagging, parsing and clustering to examine how gameplay is described. Our findings in this area highlight the primary aesthetic elements of gameplay according to the general public of game players. Finally, we show how sentiment analysis, or the classification of opinions and feelings based on the words used in a text and the relationship between those words, can be used to explore the circumstances in which certain negatively-charged words may be used positively, and for what reasons in the domain of videogames. We conclude with ideas for future research including how NLP can be used to complement other avenues of inquiry.

Natural Language Processing in Game Studies Research

Simulation & Gaming, 2012

What We Know About Games

Games and Culture, 2016

This article proposes a reflexive approach on the scientific production in the field of game studies in recent years. It relies on a sociology of science perspective to answer the question: What are game studies really about? Relying on scientometric and lexicometric tools, we analyze the metadata and content of a corpus of articles from the journals Games Studies and Games & Culture and of Digital Games Research Association ( DiGRA) proceedings. We show that published researches have been studying only a limited set of game genres and that they especially focus on online games. We then expose the different ways game studies are talking about games through a topic model analysis of our corpus. We test two hypotheses to explain the concentration of research on singular objects: path dependence and trading zone. We describe integrative properties of the focus on common objects but stress also the scientific limits met by this tendency.

Pay to Play: Understanding Gamer's Motivation through Semantic Analysis

2021

Understanding what motivates a gamer to pay to play a game could enhance the gaming industry. One of the ways to understand game players experiences is through exploration via their text communication. This study explores text communication posted on the Steam digital distribution platform on paid-play games. A total of 7255 gamer text communicated were collected and analysed. Reviews from the past pinpointed that elements such as social influence, entertaining features, graphic design, music, and soundtrack used in the game could influence the game playing experience. To study those, we use mix-method (qualitative and quantitative) methods to analyse the data. We invite three human coders to categorise statements associating with its elements and aspects. Next, with the aid of Wmatrix, a semantic analysis system, we tabulate and elaborate the emotion words associating with the gameplay elements. The result shows that the positive feeling of love and joy highly encourages the gamer's overall game playing experience. Elements such as the storyline, design of the Avatar and the entertaining features are the primary motivation of the gameplay.

A Linguistic Analysis of Mobile Games: Verbs and Nouns for Content Estimation

Foundations of Digital Games Conference 2014

This paper outlines a linguistic approach to understanding the content of games. Understanding game verbs as the fundamental unit of interaction within game environments it provides perspective on popular play experiences. The benefits of such analysis include a scalable view of the self reported content of games and the ways in which problems are being solved in games. The content of games is contrasted with the content of books for comparison. The findings indicate games are relatively limited in the diversity of verbs they use. The results also demonstrate greater emphasis on gender, and life or death in popular books than in popular mobile games. The occurrence of violent language like war and kill occur significantly more often in best-selling book descriptions than in best-selling mobile games. The most common game verbs from this research are use, touch, get, have, take, like, earn, try, create and make.

Associating Automatic Natural Language Processing to Serious Games and Virtual Worlds

Journal For Virtual Worlds Research, 2011

We present our current research activities associating automatic natural language processing to serious games and virtual worlds. Several interesting scenarios have been developed: language learning, natural language generation, multilingual information, emotion detection, real-time translations, and non-intrusive access to linguistic information such as definitions or synonyms. Part of our work has contributed to the specification of the Multi Lingual Information Framework [ISO FDIS 24616], (MLIF,2011). Standardization will grant stability, interoperability and sustainability of an important part of our research activities, in particular, in the framework of representing and managing multilingual textual information.

Developing a methodology for corpus-based computer game studies

Journal of Gaming and Virtual Worlds

Video games have become a huge success in contemporary pop culture, both as ludic devices and as narrative instruments. Because of their immense popularity they are also the didactic means in which a number of social constructs are spread and perpetuated. This is particularly true in the case of Diablo and World of Warcraft, two games produced by Blizzard Entertainment Inc. This study uses a hybrid method to study both games as texts, combining Fairclough's (2003) approach to critical discourse analysis and Corpus Linguistics. The main corpus was compiled by gathering texts about the characters in these two computer games, and their accompanying visual representations, from a) official Blizzard websites and b) user-edited websites and forums. Further data was gathered through the application of a questionnaire about male and female characters in these two games to fifty participants, and by playing each game and recording in-game interactions with non-playing characters and with other players. The linguistic data was examined using a concordancer, and then analysed following Fairclough's (2003) approach. The devised methodology places a strong emphasis in the correlation between linguistic and visual data. Through this correlation and analysis it was determined that there is a strong discourse of gender difference operating within these two games.

A Storyline-based Framework for Game Analysis Game and Media Technology

2010

When facing the problem to which extent it is possible to automatically transform a storyline definition into a game structure, the first step is to get to know how the game world should be split up into different levels. The current research tries to find out how a game could be split up into levels, based on the storyline for the game. Often in literature concepts from both the storyline and the game are used in a combined fashion. By using statements from literature together with validated assumptions, separate conceptual models are created for the storyline and game abstraction level by distributing concepts between these two levels. In order to realize the transformation from storyline to game, concepts from both levels can be linked to each other by defining relationships. These relationships are subsequently elaborated into mapping rules, which serve as a basis for the storyline ‘compiler’. The relationships between concepts from the storyline and the game imply also certain ...

A game-based corpus for analysing the interplay between game context and player experience

Affective Computing and …, 2011

Recognizing players' affective state while playing video games has been the focus of many recent research studies. In this paper we describe the process that has been followed to build a corpus based on game events and recorded video sessions from human players while playing Super Mario Bros. We present different types of information that have been extracted from game context, player preferences and perception of the game, as well as user features, automatically extracted from video recordings. We run a number of initial experiments to analyse players' behavior while playing video games as a case study of the possible use of the corpus.

What We Talk About When We Talk About Games: Bottom-Up Game Studies Using Natural Language Processing (original) (raw)

Related papers