{"title":"Predicting best answer in community questions based on content and sentiment analysis","authors":"Dalia Elalfy, Walaa K. Gad, R. Ismail","doi":"10.1109/INTELCIS.2015.7397282","DOIUrl":null,"url":null,"abstract":"Community question answering sites are gained much popularity in the last few years because of the wide spread of the internet and the facilities that these sites offer in question asking and answering processes. Community question answering sites are here to save the asker's time and effort and make him/her ask in a natural language and get the answer also back in natural language and from experts. To achieve these goals there are many challenges. Some of these challenges are for example, many questions appear to non-experts so we need to direct the questions to experts in the question category and specifying the best answer to a given question and etc. In this paper, we propose a novel model to find the best answer by using features that are based on question and answer content, answer context and the relation between question and its answers. We conducted experiments to train classifiers using our new added features and the accuracy of the best answer prediction result was very promising.","PeriodicalId":6478,"journal":{"name":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INTELCIS.2015.7397282","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Community question answering sites are gained much popularity in the last few years because of the wide spread of the internet and the facilities that these sites offer in question asking and answering processes. Community question answering sites are here to save the asker's time and effort and make him/her ask in a natural language and get the answer also back in natural language and from experts. To achieve these goals there are many challenges. Some of these challenges are for example, many questions appear to non-experts so we need to direct the questions to experts in the question category and specifying the best answer to a given question and etc. In this paper, we propose a novel model to find the best answer by using features that are based on question and answer content, answer context and the relation between question and its answers. We conducted experiments to train classifiers using our new added features and the accuracy of the best answer prediction result was very promising.