Text-Aware Graph Embeddings for Donation Behavior Prediction

MeiXing Dong, Xueming Xu, Rada Mihalcea


Abstract
Predicting user behavior is essential for a large number of applications including recommender and dialog systems, and more broadly in domains such as healthcare, education, and economics. In this paper, we show that we can effectively predict donation behavior by using text-aware graph models, building upon graphs that connect user behaviors and their interests. Using a university donation dataset, we show that the graph representation significantly improves over learning from textual representations. Moreover, we show how incorporating implicit information inferred from text associated with the graph entities brings additional improvements. Our results demonstrate the role played by text-aware graph representations in predicting donation behavior.
Anthology ID:
2022.textgraphs-1.7
Volume:
Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Dmitry Ustalov, Yanjun Gao, Alexander Panchenko, Marco Valentino, Mokanarangan Thayaparan, Thien Huu Nguyen, Gerald Penn, Arti Ramesh, Abhik Jana
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
60–69
Language:
URL:
https://aclanthology.org/2022.textgraphs-1.7
DOI:
Bibkey:
Cite (ACL):
MeiXing Dong, Xueming Xu, and Rada Mihalcea. 2022. Text-Aware Graph Embeddings for Donation Behavior Prediction. In Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing, pages 60–69, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Text-Aware Graph Embeddings for Donation Behavior Prediction (Dong et al., TextGraphs 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.textgraphs-1.7.pdf