2025
Ståhl, Matilda; Hansell, Katri; Bäck, Sandra; Wingren, Mattias
Affordances for In-Game Interaction and Language Learning Through Children's Collaborative Play in Minecraft Journal Article
In: International journal of game-based learning, vol. 15, iss. 1, 2025, ISSN: 2155-6857 .
Abstract | Links | Tags: Children's play, Children's play, Game-based learning, Minecraft, Natural language processing
@article{nokey,
title = {Affordances for In-Game Interaction and Language Learning Through Children's Collaborative Play in Minecraft},
author = {Matilda Ståhl and Katri Hansell and Sandra Bäck and Mattias Wingren},
url = {https://www.igi-global.com/gateway/article/370559},
doi = {10.4018/IJGBL.370559},
issn = {2155-6857 },
year = {2025},
date = {2025-03-05},
journal = {International journal of game-based learning},
volume = {15},
issue = {1},
abstract = {Playing video games engages children and youth and offers a potential for learning in general and situated language learning in particular. The aim of this paper is to explore the situated conditions and affordances for facilitating in-game interaction, as well as to discuss the language learning potential and educational implications of these conditions. In this paper, this is discussed through two datasets: a) a pre-study, a survey among students in grades 4–7 (n = 65), as well as b) playtests with child volunteers (n = 6), conducted in pairs in a laboratory setting. The results are discussed in relation to interactional practices, what game genres and mechanics are relevant to tandem language learning and the implications that in-game competence might have on such learning.},
keywords = {Children's play, Children's play, Game-based learning, Minecraft, Natural language processing},
pubstate = {published},
tppubtype = {article}
}
Playing video games engages children and youth and offers a potential for learning in general and situated language learning in particular. The aim of this paper is to explore the situated conditions and affordances for facilitating in-game interaction, as well as to discuss the language learning potential and educational implications of these conditions. In this paper, this is discussed through two datasets: a) a pre-study, a survey among students in grades 4–7 (n = 65), as well as b) playtests with child volunteers (n = 6), conducted in pairs in a laboratory setting. The results are discussed in relation to interactional practices, what game genres and mechanics are relevant to tandem language learning and the implications that in-game competence might have on such learning.
2021
Lu, Chien; Peltonen, Jaakko; Nummenmaa, Timo; Nummenmaa, Jyrki; Järvelin, Kalervo
Cross-structural Factor-topic Model: Document Analysis with Sophisticated Covariates Proceedings Article
In: Balasubramanian, Vineeth N.; Tsang, Ivor (Ed.): Proceedings of the 13th Asian Conference on Machine Learning, pp. 1129-1144, Asian Conference on Machine Learning, 2021, ISSN: 2640-3498.
Abstract | Links | Tags: Natural language processing, Probabilistic modeling, Topic modeling
@inproceedings{Lu2021b,
title = {Cross-structural Factor-topic Model: Document Analysis with Sophisticated Covariates},
author = {Chien Lu and Jaakko Peltonen and Timo Nummenmaa and Jyrki Nummenmaa and Kalervo Järvelin},
editor = {Vineeth N. Balasubramanian and Ivor Tsang},
url = {https://urn.fi/URN:NBN:fi:tuni-202201241538},
issn = {2640-3498},
year = {2021},
date = {2021-11-17},
urldate = {2021-11-17},
booktitle = {Proceedings of the 13th Asian Conference on Machine Learning},
pages = {1129-1144},
publisher = {Asian Conference on Machine Learning},
abstract = {Modern text data is increasingly gathered in situations where it is paired with a high-dimensional collection of covariates: then both the text, the covariates, and their relationships are of interest to analyze. Despite the growing amount of such data, current topic models are unable to take into account large amounts of covariates successfully: they fail to model structure among covariates and distort findings of both text and covariates. This paper presents a solution: a novel factor-topic model that enables researchers to analyze latent structure in both text and sophisticated document-level covariates collectively. The key innovation is that besides learning the underlying topical structure, the model also learns the underlying factorial structure from the covariates and the interactions between the two structures. A set of tailored variational inference algorithms for efficient computation are provided. Experiments on three different datasets show the model outperforms comparable topic models in the ability to predict held-out document content. Two case studies focusing on Finnish parliamentary election candidates and game players on Steam demonstrate the model discovers semantically meaningful topics, factors, and their interactions. The model both outperforms state-of-the-art models in predictive accuracy and offers new factor-topic insights beyond other topic models.},
keywords = {Natural language processing, Probabilistic modeling, Topic modeling},
pubstate = {published},
tppubtype = {inproceedings}
}
Modern text data is increasingly gathered in situations where it is paired with a high-dimensional collection of covariates: then both the text, the covariates, and their relationships are of interest to analyze. Despite the growing amount of such data, current topic models are unable to take into account large amounts of covariates successfully: they fail to model structure among covariates and distort findings of both text and covariates. This paper presents a solution: a novel factor-topic model that enables researchers to analyze latent structure in both text and sophisticated document-level covariates collectively. The key innovation is that besides learning the underlying topical structure, the model also learns the underlying factorial structure from the covariates and the interactions between the two structures. A set of tailored variational inference algorithms for efficient computation are provided. Experiments on three different datasets show the model outperforms comparable topic models in the ability to predict held-out document content. Two case studies focusing on Finnish parliamentary election candidates and game players on Steam demonstrate the model discovers semantically meaningful topics, factors, and their interactions. The model both outperforms state-of-the-art models in predictive accuracy and offers new factor-topic insights beyond other topic models.