{"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/mining-fine-grained-opinions-on-closed","title":"Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN","arxiv_id":"1708.02420","date":"2017-08-08","proceeding":"WS 2017 9","authors":["Edison Marrese-Taylor","Jorge A. Balazs","Yutaka Matsuo"],"abstract":"Video reviews are the natural evolution of written product reviews. In this\npaper we target this phenomenon and introduce the first dataset created from\nclosed captions of YouTube product review videos as well as a new attention-RNN\nmodel for aspect extraction and joint aspect extraction and sentiment\nclassification. Our model provides state-of-the-art performance on aspect\nextraction without requiring the usage of hand-crafted features on the SemEval\nABSA corpus, while it outperforms the baseline on the joint task. In our\ndataset, the attention-RNN model outperforms the baseline for both tasks, but\nwe observe important performance drops for all models in comparison to SemEval.\nThese results, as well as further experiments on domain adaptation for aspect\nextraction, suggest that differences between speech and written text, which\nhave been discussed extensively in the literature, also extend to the domain of\nproduct reviews, where they are relevant for fine-grained opinion mining.","url_abs":"http://arxiv.org/abs/1708.02420v1","url_pdf":"http://arxiv.org/pdf/1708.02420v1.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":"mining-fine-grained-opinions-on-closed","repo_url":"https://github.com/epochx/opinatt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"aspect-extraction","task_name":"Aspect Extraction"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"opinion-mining","task_name":"Opinion Mining"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[{"slug":"youtubean","name":"Youtubean","full_name":null}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}