{"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/w2vlda-almost-unsupervised-system-for-aspect","title":"W2VLDA: Almost Unsupervised System for Aspect Based Sentiment Analysis","arxiv_id":"1705.07687","date":"2017-05-22","proceeding":null,"authors":["Aitor García-Pablos","Montse Cuadros","German Rigau"],"abstract":"With the increase of online customer opinions in specialised websites and\nsocial networks, the necessity of automatic systems to help to organise and\nclassify customer reviews by domain-specific aspect/categories and sentiment\npolarity is more important than ever. Supervised approaches to Aspect Based\nSentiment Analysis obtain good results for the domain/language their are\ntrained on, but having manually labelled data for training supervised systems\nfor all domains and languages are usually very costly and time consuming. In\nthis work we describe W2VLDA, an almost unsupervised system based on topic\nmodelling, that combined with some other unsupervised methods and a minimal\nconfiguration, performs aspect/category classifiation,\naspect-terms/opinion-words separation and sentiment polarity classification for\nany given domain and language. We evaluate the performance of the aspect and\nsentiment classification in the multilingual SemEval 2016 task 5 (ABSA)\ndataset. We show competitive results for several languages (English, Spanish,\nFrench and Dutch) and domains (hotels, restaurants, electronic-devices).","url_abs":"http://arxiv.org/abs/1705.07687v2","url_pdf":"http://arxiv.org/pdf/1705.07687v2.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":"w2vlda-almost-unsupervised-system-for-aspect","repo_url":"https://bitbucket.org/aitor-garcia-p/w2vlda-last","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.07687","atlas_url":"https://app.syntology.ai/?focus=1705.07687","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}