Heterogeneous Information Network Embedding for Mention Recommendation
Mention recommendation is the task of recommending the right candidate users in a message. Many works have been conducted on the problem of whom to mention. However, due to the sparsity and heterogeneous of mention data, none of them well solve the problem. The recent advances in network embedding r...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9093049/ |
| _version_ | 1818064960070090752 |
|---|---|
| author | Feng Yi Bo Jiang Jianjun Wu |
| author_facet | Feng Yi Bo Jiang Jianjun Wu |
| author_sort | Feng Yi |
| collection | DOAJ |
| description | Mention recommendation is the task of recommending the right candidate users in a message. Many works have been conducted on the problem of whom to mention. However, due to the sparsity and heterogeneous of mention data, none of them well solve the problem. The recent advances in network embedding representation learning provide an effective approach to model the sparsity and heterogeneous simultaneously in heterogeneous information network. To this end, we propose a novel Network Embedding Mention (NEM) recommendation model to recommend the right users in a message. NEM constructs a heterogeneous mention network based on different relationships among different entities. Then NEM learns a unified low dimensional embedding vector using random walk for users and messages by considering network structure and vertex content information. Finally, whom to mention is ranked by calculating the relevance scores from heterogeneous user and message embeddings. To evaluate the proposed method, we construct a large dataset and their corresponding social networks from a real-world social media platform. Through extensive experiments on real-world mention collection, we demonstrate that our proposed model outperforms the previous state-of-the-art methods in term of recommendation task. |
| first_indexed | 2024-12-10T14:44:17Z |
| format | Article |
| id | doaj.art-1216e1cbec944e909ac92f5f6e4d24e0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T14:44:17Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1216e1cbec944e909ac92f5f6e4d24e02022-12-22T01:44:36ZengIEEEIEEE Access2169-35362020-01-018913949140410.1109/ACCESS.2020.29943139093049Heterogeneous Information Network Embedding for Mention RecommendationFeng Yi0https://orcid.org/0000-0002-3253-5232Bo Jiang1https://orcid.org/0000-0002-7185-990XJianjun Wu2https://orcid.org/0000-0002-7801-0773School of Computer Science, Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan, ChinaInstitute of Information Engineering, Chinese Academy of Sciences, Beijing, ChinaBeijing College of Politics and Law, Beijing, ChinaMention recommendation is the task of recommending the right candidate users in a message. Many works have been conducted on the problem of whom to mention. However, due to the sparsity and heterogeneous of mention data, none of them well solve the problem. The recent advances in network embedding representation learning provide an effective approach to model the sparsity and heterogeneous simultaneously in heterogeneous information network. To this end, we propose a novel Network Embedding Mention (NEM) recommendation model to recommend the right users in a message. NEM constructs a heterogeneous mention network based on different relationships among different entities. Then NEM learns a unified low dimensional embedding vector using random walk for users and messages by considering network structure and vertex content information. Finally, whom to mention is ranked by calculating the relevance scores from heterogeneous user and message embeddings. To evaluate the proposed method, we construct a large dataset and their corresponding social networks from a real-world social media platform. Through extensive experiments on real-world mention collection, we demonstrate that our proposed model outperforms the previous state-of-the-art methods in term of recommendation task.https://ieeexplore.ieee.org/document/9093049/Mention recommendationnetwork embeddingrelation networkheterogeneous information |
| spellingShingle | Feng Yi Bo Jiang Jianjun Wu Heterogeneous Information Network Embedding for Mention Recommendation IEEE Access Mention recommendation network embedding relation network heterogeneous information |
| title | Heterogeneous Information Network Embedding for Mention Recommendation |
| title_full | Heterogeneous Information Network Embedding for Mention Recommendation |
| title_fullStr | Heterogeneous Information Network Embedding for Mention Recommendation |
| title_full_unstemmed | Heterogeneous Information Network Embedding for Mention Recommendation |
| title_short | Heterogeneous Information Network Embedding for Mention Recommendation |
| title_sort | heterogeneous information network embedding for mention recommendation |
| topic | Mention recommendation network embedding relation network heterogeneous information |
| url | https://ieeexplore.ieee.org/document/9093049/ |
| work_keys_str_mv | AT fengyi heterogeneousinformationnetworkembeddingformentionrecommendation AT bojiang heterogeneousinformationnetworkembeddingformentionrecommendation AT jianjunwu heterogeneousinformationnetworkembeddingformentionrecommendation |