Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation
Tremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. Ho...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/2/1093 |
| _version_ | 1827628937280225280 |
|---|---|
| author | Wei Chen Yihao Zhang Yantuan Xian Yonghua Wen |
| author_facet | Wei Chen Yihao Zhang Yantuan Xian Yonghua Wen |
| author_sort | Wei Chen |
| collection | DOAJ |
| description | Tremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. However, these models lack a more comprehensive analysis of the connections between the literature, the domain knowledge provided, and the hotspot information expressed in the literature. Previous models make it impossible to locate the appropriate documents for domain literature. Additionally, these models encounter problems such as cold start papers and data sparsity. To overcome these problems, this paper presents a recommendation model termed PRHN. Inputs of the model are the hotspot information network and the domain knowledge graph, which both were developed during the preceding research phase. After the query terms are extracted and the associated heterogeneous literature networks are formed, they are aggregated in a uniform hidden space. Similarity with the candidate set is determined to transform the search problem into a TOP <i>N</i> recommendation problem. Compared to state-of-the-art models, results generated by PRHN on public available datasets show improvement in HR and NDCG. Concretely, results on the metallurgical literature dataset are more conspicuous, with more remarkable improvement in HR and NGCC by approximately 4.5% and 4.2%. |
| first_indexed | 2024-03-09T13:41:45Z |
| format | Article |
| id | doaj.art-d3dd8afc18734908848515199831010f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:41:45Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d3dd8afc18734908848515199831010f2023-11-30T21:06:06ZengMDPI AGApplied Sciences2076-34172023-01-01132109310.3390/app13021093Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature RecommendationWei Chen0Yihao Zhang1Yantuan Xian2Yonghua Wen3School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaSchool of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaSchool of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaSchool of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaTremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. However, these models lack a more comprehensive analysis of the connections between the literature, the domain knowledge provided, and the hotspot information expressed in the literature. Previous models make it impossible to locate the appropriate documents for domain literature. Additionally, these models encounter problems such as cold start papers and data sparsity. To overcome these problems, this paper presents a recommendation model termed PRHN. Inputs of the model are the hotspot information network and the domain knowledge graph, which both were developed during the preceding research phase. After the query terms are extracted and the associated heterogeneous literature networks are formed, they are aggregated in a uniform hidden space. Similarity with the candidate set is determined to transform the search problem into a TOP <i>N</i> recommendation problem. Compared to state-of-the-art models, results generated by PRHN on public available datasets show improvement in HR and NDCG. Concretely, results on the metallurgical literature dataset are more conspicuous, with more remarkable improvement in HR and NGCC by approximately 4.5% and 4.2%.https://www.mdpi.com/2076-3417/13/2/1093knowledge graphhotspot information networkheterogeneous academic networkrecommender system |
| spellingShingle | Wei Chen Yihao Zhang Yantuan Xian Yonghua Wen Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation Applied Sciences knowledge graph hotspot information network heterogeneous academic network recommender system |
| title | Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation |
| title_full | Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation |
| title_fullStr | Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation |
| title_full_unstemmed | Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation |
| title_short | Hotspot Information Network and Domain Knowledge Graph Aggregation in Heterogeneous Network for Literature Recommendation |
| title_sort | hotspot information network and domain knowledge graph aggregation in heterogeneous network for literature recommendation |
| topic | knowledge graph hotspot information network heterogeneous academic network recommender system |
| url | https://www.mdpi.com/2076-3417/13/2/1093 |
| work_keys_str_mv | AT weichen hotspotinformationnetworkanddomainknowledgegraphaggregationinheterogeneousnetworkforliteraturerecommendation AT yihaozhang hotspotinformationnetworkanddomainknowledgegraphaggregationinheterogeneousnetworkforliteraturerecommendation AT yantuanxian hotspotinformationnetworkanddomainknowledgegraphaggregationinheterogeneousnetworkforliteraturerecommendation AT yonghuawen hotspotinformationnetworkanddomainknowledgegraphaggregationinheterogeneousnetworkforliteraturerecommendation |