Predicting choice behaviour in economic games using gaze data encoded as scanpath images
Abstract Eye movement data has been extensively utilized by researchers interested in studying decision-making within the strategic setting of economic games. In this paper, we demonstrate that both deep learning and support vector machine classification methods are able to accurately identify parti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-31536-5 |
| _version_ | 1797859987906625536 |
|---|---|
| author | Sean Anthony Byrne Adam Peter Frederick Reynolds Carolina Biliotti Falco J. Bargagli-Stoffi Luca Polonio Massimo Riccaboni |
| author_facet | Sean Anthony Byrne Adam Peter Frederick Reynolds Carolina Biliotti Falco J. Bargagli-Stoffi Luca Polonio Massimo Riccaboni |
| author_sort | Sean Anthony Byrne |
| collection | DOAJ |
| description | Abstract Eye movement data has been extensively utilized by researchers interested in studying decision-making within the strategic setting of economic games. In this paper, we demonstrate that both deep learning and support vector machine classification methods are able to accurately identify participants’ decision strategies before they commit to action while playing games. Our approach focuses on creating scanpath images that best capture the dynamics of a participant’s gaze behaviour in a way that is meaningful for predictions to the machine learning models. Our results demonstrate a higher classification accuracy by 18% points compared to a baseline logistic regression model, which is traditionally used to analyse gaze data recorded during economic games. In a broader context, we aim to illustrate the potential for eye-tracking data to create information asymmetries in strategic environments in favour of those who collect and process the data. These information asymmetries could become especially relevant as eye-tracking is expected to become more widespread in user applications, with the seemingly imminent mass adoption of virtual reality systems and the development of devices with the ability to record eye movement outside of a laboratory setting. |
| first_indexed | 2024-04-09T21:38:28Z |
| format | Article |
| id | doaj.art-e46fa7b4972e44658a030b214543765a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T21:38:28Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e46fa7b4972e44658a030b214543765a2023-03-26T11:10:17ZengNature PortfolioScientific Reports2045-23222023-03-0113111310.1038/s41598-023-31536-5Predicting choice behaviour in economic games using gaze data encoded as scanpath imagesSean Anthony Byrne0Adam Peter Frederick Reynolds1Carolina Biliotti2Falco J. Bargagli-Stoffi3Luca Polonio4Massimo Riccaboni5MoMiLab Research Unit, IMT School for Advanced Studies LuccaMoMiLab Research Unit, IMT School for Advanced Studies LuccaAXES Research Unit, IMT School for Advanced Studies LuccaDepartment of Biostatistics, Harvard UniversityDepartment of Economics, Management and Statistics, University of Milano - BicoccaAXES Research Unit, IMT School for Advanced Studies LuccaAbstract Eye movement data has been extensively utilized by researchers interested in studying decision-making within the strategic setting of economic games. In this paper, we demonstrate that both deep learning and support vector machine classification methods are able to accurately identify participants’ decision strategies before they commit to action while playing games. Our approach focuses on creating scanpath images that best capture the dynamics of a participant’s gaze behaviour in a way that is meaningful for predictions to the machine learning models. Our results demonstrate a higher classification accuracy by 18% points compared to a baseline logistic regression model, which is traditionally used to analyse gaze data recorded during economic games. In a broader context, we aim to illustrate the potential for eye-tracking data to create information asymmetries in strategic environments in favour of those who collect and process the data. These information asymmetries could become especially relevant as eye-tracking is expected to become more widespread in user applications, with the seemingly imminent mass adoption of virtual reality systems and the development of devices with the ability to record eye movement outside of a laboratory setting.https://doi.org/10.1038/s41598-023-31536-5 |
| spellingShingle | Sean Anthony Byrne Adam Peter Frederick Reynolds Carolina Biliotti Falco J. Bargagli-Stoffi Luca Polonio Massimo Riccaboni Predicting choice behaviour in economic games using gaze data encoded as scanpath images Scientific Reports |
| title | Predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| title_full | Predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| title_fullStr | Predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| title_full_unstemmed | Predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| title_short | Predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| title_sort | predicting choice behaviour in economic games using gaze data encoded as scanpath images |
| url | https://doi.org/10.1038/s41598-023-31536-5 |
| work_keys_str_mv | AT seananthonybyrne predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages AT adampeterfrederickreynolds predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages AT carolinabiliotti predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages AT falcojbargaglistoffi predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages AT lucapolonio predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages AT massimoriccaboni predictingchoicebehaviourineconomicgamesusinggazedataencodedasscanpathimages |