%0 Journal Article %1 2015 %A Ganesan, Kavita %A Zhai, ChengXiang %D 2015 %J Information Retrieval Journal %K crawler myown review_crawling web_crawling %T OpinoFetch: A Pratical Unsupervised Approach to Collecting Opinions on Arbitrary Entities %U http://kavita-ganesan.com/content/opinofetch-pratical-unsupervised-approach-collecting-opinions-arbitrary-entities %X The abundance of opinions on the Web is now becoming a critical source of information in a variety of application areas such as business intelligence, market research and online shopping. Unfortunately, due to the rapid growth of online content, there is no one source to obtain a comprehensive set of opinions about a specific entity or a topic, making access to such content severely limited. While previous works have been focused on mining and summarizing online opinions, there is limited work on exploring the automatic collection of online opinions. In this paper, we propose a lightweight and unsupervised approach to collecting opinions namely reviews on the web for arbitrary entities. We leverage existing web search engines and use a novel information network called the FetchGraph to efficiently obtain review pages for entities of interest. Our experiments in three different domains show that our method is more effective than plain search engine results and we are able to collect entity specific review pages efficiently with reasonable accuracy.

@article{2015, abstract = {The abundance of opinions on the Web is now becoming a critical source of information in a variety of application areas such as business intelligence, market research and online shopping. Unfortunately, due to the rapid growth of online content, there is no one source to obtain a comprehensive set of opinions about a specific entity or a topic, making access to such content severely limited. While previous works have been focused on mining and summarizing online opinions, there is limited work on exploring the automatic collection of online opinions. In this paper, we propose a lightweight and unsupervised approach to collecting opinions namely reviews on the web for arbitrary entities. We leverage existing web search engines and use a novel information network called the FetchGraph to efficiently obtain review pages for entities of interest. Our experiments in three different domains show that our method is more effective than plain search engine results and we are able to collect entity specific review pages efficiently with reasonable accuracy.}, added-at = {2014-12-16T06:40:56.000+0100}, attachments = {http://kavita-ganesan.com/sites/default/files/opinofetch.pdf}, author = {Ganesan, Kavita and Zhai, ChengXiang}, biburl = {https://www.bibsonomy.org/bibtex/2e700b9b4f32ef61c0c7e76160f846542/kavitaxx}, interhash = {3f5fcfd7799fb3326440eaeb357089c8}, intrahash = {e700b9b4f32ef61c0c7e76160f846542}, journal = {Information Retrieval Journal}, keywords = {crawler myown review_crawling web_crawling}, timestamp = {2014-12-16T06:40:56.000+0100}, title = {OpinoFetch: A Pratical Unsupervised Approach to Collecting Opinions on Arbitrary Entities}, url = {http://kavita-ganesan.com/content/opinofetch-pratical-unsupervised-approach-collecting-opinions-arbitrary-entities}, year = 2015 }