{"title":"一种用于管理部门情绪估计的商业智能技术","authors":"S. Rady","doi":"10.1109/INTELCIS.2015.7397247","DOIUrl":null,"url":null,"abstract":"People express emotions in response to everyday situation and personal communication. With diversity of language expressions, it is challenging to provide an accurate estimation of emotion or sentiment. This paper proposes intelligent technique and system for sentiment estimation and prediction in the business domain. It is useful for management sectors where tools can automatically analyze collected data and reveal employees' opinion about their organization, or any ongoing topic. The challenge in this work is to detect sentiment classes from relatively long text, where writers merge sentences and expressions when asked to write reviews, instead of being directly asked to write their sentiment degree. The approach is data-driven, which uses machine learning to train classifier features to recognize the sentiment. A system is implemented and tested (on real data collected from employee reviews at big IT organizations) towards two and five classification degrees problems. Recorded results prove efficiency of the technique.","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":"1","resultStr":"{\"title\":\"A business intelligent technique for sentiment estimation by management sectors\",\"authors\":\"S. Rady\",\"doi\":\"10.1109/INTELCIS.2015.7397247\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"People express emotions in response to everyday situation and personal communication. With diversity of language expressions, it is challenging to provide an accurate estimation of emotion or sentiment. This paper proposes intelligent technique and system for sentiment estimation and prediction in the business domain. It is useful for management sectors where tools can automatically analyze collected data and reveal employees' opinion about their organization, or any ongoing topic. The challenge in this work is to detect sentiment classes from relatively long text, where writers merge sentences and expressions when asked to write reviews, instead of being directly asked to write their sentiment degree. The approach is data-driven, which uses machine learning to train classifier features to recognize the sentiment. A system is implemented and tested (on real data collected from employee reviews at big IT organizations) towards two and five classification degrees problems. Recorded results prove efficiency of the technique.\",\"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\":\"1\",\"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.2015.7397247\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","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.2015.7397247","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A business intelligent technique for sentiment estimation by management sectors
People express emotions in response to everyday situation and personal communication. With diversity of language expressions, it is challenging to provide an accurate estimation of emotion or sentiment. This paper proposes intelligent technique and system for sentiment estimation and prediction in the business domain. It is useful for management sectors where tools can automatically analyze collected data and reveal employees' opinion about their organization, or any ongoing topic. The challenge in this work is to detect sentiment classes from relatively long text, where writers merge sentences and expressions when asked to write reviews, instead of being directly asked to write their sentiment degree. The approach is data-driven, which uses machine learning to train classifier features to recognize the sentiment. A system is implemented and tested (on real data collected from employee reviews at big IT organizations) towards two and five classification degrees problems. Recorded results prove efficiency of the technique.