{"id":{"repo_id":"carleton","oai_identifier":"oai:carleton.scholaris.ca:20.500.14718/42416"},"canonical_url":"https://search.dev.ndltd.org/etd/carleton/oai:carleton.scholaris.ca:20.500.14718/42416","repository":{"repo_id":"carleton","name":"Carleton University","base_url":"https://carleton.scholaris.ca/server/oai/request"},"display":{"title":"Vector Embedding Techniques for Player Behaviour in DOTA 2","abstract":"Personalization applications need prior information about a user, and popular techniques that use neural networks need data in a numerical format. This work explores three node embedding techniques to represent player behaviour in a compact vector form. I used data from the game DOTA 2 to produce vectors using three graph embedding methods, developed a testing framework, and conducted 270 experiments to explore the effect of different parameters on vector quality. I explored different values for parameters, including the number of vector dimensions, the number of games, the types of interactions used in training, and step size for updating vectors over time. The results show that using node2vec and a vector dimension of 512 outperforms the other methods in 13 of the 15 parameter variations that I tested. node2vec also computed the vectors 60 and 10 times faster than LINE and TGN, respectively, on the same amount of data.","abstract_html":"Personalization applications need prior information about a user, and popular techniques that use neural networks need data in a numerical format. This work explores three node embedding techniques to represent player behaviour in a compact vector form. I used data from the game DOTA 2 to produce vectors using three graph embedding methods, developed a testing framework, and conducted 270 experiments to explore the effect of different parameters on vector quality. I explored different values for parameters, including the number of vector dimensions, the number of games, the types of interactions used in training, and step size for updating vectors over time. The results show that using node2vec and a vector dimension of 512 outperforms the other methods in 13 of the 15 parameter variations that I tested. node2vec also computed the vectors 60 and 10 times faster than LINE and TGN, respectively, on the same amount of data.","abstract_has_math":false,"creators":["Shah, Jinay Gautamkumar"],"institution":"Carleton University","degree_name":"Master of Information Technology (M.I.T.)","degree_level":"Master's","degree_discipline":"Digital Media","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021","date_published":"2021","updated_at":"2026-07-24T01:34:45Z","subjects":[],"languages":["en"],"rights":["Copyright © 2021 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2021-14680"],"render_values":[{"text":"10.22215/etd/2021-14680","href":"https://doi.org/10.22215/etd/2021-14680","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14718/42416","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Shah, Jinay Gautamkumar"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-08T20:37:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-08T20:37:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2021"]},{"key":"dc:publisher","label":"Institution","values":["Carleton University"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Digital Media"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Information Technology (M.I.T.)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2021 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2021-14680"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14718/42416"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Personalization applications need prior information about a user, and popular techniques that use neural networks need data in a numerical format. This work explores three node embedding techniques to represent player behaviour in a compact vector form. I used data from the game DOTA 2 to produce vectors using three graph embedding methods, developed a testing framework, and conducted 270 experiments to explore the effect of different parameters on vector quality. I explored different values for parameters, including the number of vector dimensions, the number of games, the types of interactions used in training, and step size for updating vectors over time. The results show that using node2vec and a vector dimension of 512 outperforms the other methods in 13 of the 15 parameter variations that I tested. node2vec also computed the vectors 60 and 10 times faster than LINE and TGN, respectively, on the same amount of data."]},{"key":"dc:title","label":"Title","values":["Vector Embedding Techniques for Player Behaviour in DOTA 2"]}]}],"canonical_facts":{"dc:creator":["Shah, Jinay Gautamkumar"],"dc:date.accessioned":["2025-04-08T20:37:17Z"],"dc:date.available":["2025-04-08T20:37:17Z"],"dc:date.issued":["2021"],"dc:description.abstract":["Personalization applications need prior information about a user, and popular techniques that use neural networks need data in a numerical format. This work explores three node embedding techniques to represent player behaviour in a compact vector form. I used data from the game DOTA 2 to produce vectors using three graph embedding methods, developed a testing framework, and conducted 270 experiments to explore the effect of different parameters on vector quality. I explored different values for parameters, including the number of vector dimensions, the number of games, the types of interactions used in training, and step size for updating vectors over time. The results show that using node2vec and a vector dimension of 512 outperforms the other methods in 13 of the 15 parameter variations that I tested. node2vec also computed the vectors 60 and 10 times faster than LINE and TGN, respectively, on the same amount of data."],"dc:identifier.doi":["10.22215/etd/2021-14680"],"dc:identifier.uri":["https://hdl.handle.net/20.500.14718/42416"],"dc:language.iso":["en"],"dc:publisher":["Carleton University"],"dc:rights":["Copyright © 2021 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"dc:title":["Vector Embedding Techniques for Player Behaviour in DOTA 2"],"dc:type":["thesis"],"thesis:degree_discipline":["Digital Media"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Information Technology (M.I.T.)"]},"updated_at":"2026-07-24T01:34:45Z"}