Unsupervised Learning of Domain-Independent User Attributes
Learning user attributes is essential for providing users with a service. In particular, for e-commerce portals which deal in variety of goods ranging from clothes to foods to home electronics, it is especially important to learn “domain-independent” attributes such as age, gen...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9943550/ |
| _version_ | 1811220169762013184 |
|---|---|
| author | Yuichi Ishikawa Roberto Legaspi Kei Yonekawa Yugo Nakamura Shigemi Ishida Tsunenori Mine Yutaka Arakawa |
| author_facet | Yuichi Ishikawa Roberto Legaspi Kei Yonekawa Yugo Nakamura Shigemi Ishida Tsunenori Mine Yutaka Arakawa |
| author_sort | Yuichi Ishikawa |
| collection | DOAJ |
| description | Learning user attributes is essential for providing users with a service. In particular, for e-commerce portals which deal in variety of goods ranging from clothes to foods to home electronics, it is especially important to learn “domain-independent” attributes such as age, gender, and personality that affect people’s behavior across various domains of daily life (e.g., clothing, eating and housing) because these attributes can be used for personalization in diverse domains their service covers. Thus far, researchers have proposed approaches to learn user representation (UR) from user-item interactions, trying to embed rich information about user attributes in UR. However, very few can learn URs that are domain-independent without confounding them with domain-specific attributes (e.g., food preferences). This could consequently undermine the former’s utility for personalizing services in other domains from which the URs are not learned. To address this, we propose an approach to learn URs that exclusively reflect domain-independent attributes. Our approach introduces a novel multi-layer RNN with two types of layers: Domain Specific Layers (DSLs) for modeling behavior in individual domains and a Domain Independent Layer (DIL) for modeling attributes that affect behavior across multiple domains. By exchanging hidden states between these layers, the RNNs implement the process of domain-independent attributes affecting domain-specific behavior and makes the DIL learn URs that capture domain-independence. Our evaluation results confirmed that the URs learned by our approach have greater utility in predicting behavior in the other domains from which these URs were not learned thereby demonstrating adaptability to various domains. |
| first_indexed | 2024-04-12T07:36:57Z |
| format | Article |
| id | doaj.art-a69d38ca9f9b4096881a072c03c28da3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T07:36:57Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a69d38ca9f9b4096881a072c03c28da32022-12-22T03:41:54ZengIEEEIEEE Access2169-35362022-01-011011964911966510.1109/ACCESS.2022.32207819943550Unsupervised Learning of Domain-Independent User AttributesYuichi Ishikawa0https://orcid.org/0000-0003-3000-9113Roberto Legaspi1Kei Yonekawa2https://orcid.org/0000-0002-4349-8895Yugo Nakamura3https://orcid.org/0000-0002-8834-5323Shigemi Ishida4https://orcid.org/0000-0003-0166-3984Tsunenori Mine5https://orcid.org/0000-0002-7462-8074Yutaka Arakawa6https://orcid.org/0000-0002-7156-9160Faculty of Information Science, Kyushu University, Nishi-ku, Fukuoka-shi, Fukuoka, JapanKDDI Research Inc., Fujimino-shi, Saitama, JapanKDDI Research Inc., Fujimino-shi, Saitama, JapanFaculty of Information Science, Kyushu University, Nishi-ku, Fukuoka-shi, Fukuoka, JapanDepartment of Media Architecture, School of Systems Information Science, Future University Hakodate, Hakodate, JapanFaculty of Information Science, Kyushu University, Nishi-ku, Fukuoka-shi, Fukuoka, JapanFaculty of Information Science, Kyushu University, Nishi-ku, Fukuoka-shi, Fukuoka, JapanLearning user attributes is essential for providing users with a service. In particular, for e-commerce portals which deal in variety of goods ranging from clothes to foods to home electronics, it is especially important to learn “domain-independent” attributes such as age, gender, and personality that affect people’s behavior across various domains of daily life (e.g., clothing, eating and housing) because these attributes can be used for personalization in diverse domains their service covers. Thus far, researchers have proposed approaches to learn user representation (UR) from user-item interactions, trying to embed rich information about user attributes in UR. However, very few can learn URs that are domain-independent without confounding them with domain-specific attributes (e.g., food preferences). This could consequently undermine the former’s utility for personalizing services in other domains from which the URs are not learned. To address this, we propose an approach to learn URs that exclusively reflect domain-independent attributes. Our approach introduces a novel multi-layer RNN with two types of layers: Domain Specific Layers (DSLs) for modeling behavior in individual domains and a Domain Independent Layer (DIL) for modeling attributes that affect behavior across multiple domains. By exchanging hidden states between these layers, the RNNs implement the process of domain-independent attributes affecting domain-specific behavior and makes the DIL learn URs that capture domain-independence. Our evaluation results confirmed that the URs learned by our approach have greater utility in predicting behavior in the other domains from which these URs were not learned thereby demonstrating adaptability to various domains.https://ieeexplore.ieee.org/document/9943550/Big Fivee-commercepersonalityRNNuser modelinguser representation learning |
| spellingShingle | Yuichi Ishikawa Roberto Legaspi Kei Yonekawa Yugo Nakamura Shigemi Ishida Tsunenori Mine Yutaka Arakawa Unsupervised Learning of Domain-Independent User Attributes IEEE Access Big Five e-commerce personality RNN user modeling user representation learning |
| title | Unsupervised Learning of Domain-Independent User Attributes |
| title_full | Unsupervised Learning of Domain-Independent User Attributes |
| title_fullStr | Unsupervised Learning of Domain-Independent User Attributes |
| title_full_unstemmed | Unsupervised Learning of Domain-Independent User Attributes |
| title_short | Unsupervised Learning of Domain-Independent User Attributes |
| title_sort | unsupervised learning of domain independent user attributes |
| topic | Big Five e-commerce personality RNN user modeling user representation learning |
| url | https://ieeexplore.ieee.org/document/9943550/ |
| work_keys_str_mv | AT yuichiishikawa unsupervisedlearningofdomainindependentuserattributes AT robertolegaspi unsupervisedlearningofdomainindependentuserattributes AT keiyonekawa unsupervisedlearningofdomainindependentuserattributes AT yugonakamura unsupervisedlearningofdomainindependentuserattributes AT shigemiishida unsupervisedlearningofdomainindependentuserattributes AT tsunenorimine unsupervisedlearningofdomainindependentuserattributes AT yutakaarakawa unsupervisedlearningofdomainindependentuserattributes |