{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shine-signed-heterogeneous-information","title":"SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction","arxiv_id":"1712.00732","date":"2017-12-03","proceeding":null,"authors":["Hongwei Wang","Fuzheng Zhang","Min Hou","Xing Xie","Minyi Guo","Qi Liu"],"abstract":"In online social networks people often express attitudes towards others,\nwhich forms massive sentiment links among users. Predicting the sign of\nsentiment links is a fundamental task in many areas such as personal\nadvertising and public opinion analysis. Previous works mainly focus on textual\nsentiment classification, however, text information can only disclose the \"tip\nof the iceberg\" about users' true opinions, of which the most are unobserved\nbut implied by other sources of information such as social relation and users'\nprofile. To address this problem, in this paper we investigate how to predict\npossibly existing sentiment links in the presence of heterogeneous information.\nFirst, due to the lack of explicit sentiment links in mainstream social\nnetworks, we establish a labeled heterogeneous sentiment dataset which consists\nof users' sentiment relation, social relation and profile knowledge by\nentity-level sentiment extraction method. Then we propose a novel and flexible\nend-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework\nto extract users' latent representations from heterogeneous networks and\npredict the sign of unobserved sentiment links. SHINE utilizes multiple deep\nautoencoders to map each user into a low-dimension feature space while\npreserving the network structure. We demonstrate the superiority of SHINE over\nstate-of-the-art baselines on link prediction and node recommendation in two\nreal-world datasets. The experimental results also prove the efficacy of SHINE\nin cold start scenario.","url_abs":"http://arxiv.org/abs/1712.00732v1","url_pdf":"http://arxiv.org/pdf/1712.00732v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shine-signed-heterogeneous-information","repo_url":"https://github.com/boom85423/hello_SHINE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"network-embedding","task_name":"Network Embedding"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.00732","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}