Opinion mining from user reviews

2015 International Conference on Technologies for Sustainable Development (ICTSD) Pub Date : 2015-04-30 DOI:10.1109/ICTSD.2015.7095904

A. Tripathy, Revathy. Sundararajan, C. Deshpande, Pankaj Mishra, N. Natarajan

{"title":"Opinion mining from user reviews","authors":"A. Tripathy, Revathy. Sundararajan, C. Deshpande, Pankaj Mishra, N. Natarajan","doi":"10.1109/ICTSD.2015.7095904","DOIUrl":null,"url":null,"abstract":"Due to advancement of technology and mainly Internet, the concept of marketing and selling of product has reached to a new level. Now-a-days, lots of companies rely on user reviews for launching their product. These reviews play an important role or companies to know how their product has been accepted in the market. But, today, thousands of reviews are generated for a product. Companies have to process each of these reviews to get user opinion as well as ideas, which is a very tedious and time-consuming. This paper discourses about extracting opinions from the user reviews is semi-automatic, in the sense that it requires some amount of expert assistance. Expert assistance is required for building the domain knowledge for the system, so as to make the system learn about the domain specific words]. The proposed system, using domain knowledge, identifies and extracts the opinions for a given product. These extracted opinions include the opinion words, their polarity in from of weights and for which feature these opinions was provided and system aggregates the extracted opinions them for better display.","PeriodicalId":270099,"journal":{"name":"2015 International Conference on Technologies for Sustainable Development (ICTSD)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2015-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Technologies for Sustainable Development (ICTSD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTSD.2015.7095904","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

Due to advancement of technology and mainly Internet, the concept of marketing and selling of product has reached to a new level. Now-a-days, lots of companies rely on user reviews for launching their product. These reviews play an important role or companies to know how their product has been accepted in the market. But, today, thousands of reviews are generated for a product. Companies have to process each of these reviews to get user opinion as well as ideas, which is a very tedious and time-consuming. This paper discourses about extracting opinions from the user reviews is semi-automatic, in the sense that it requires some amount of expert assistance. Expert assistance is required for building the domain knowledge for the system, so as to make the system learn about the domain specific words]. The proposed system, using domain knowledge, identifies and extracts the opinions for a given product. These extracted opinions include the opinion words, their polarity in from of weights and for which feature these opinions was provided and system aggregates the extracted opinions them for better display.

查看原文本刊更多论文

从用户评论中挖掘意见

由于技术的进步，主要是互联网，营销和销售产品的概念已经达到了一个新的水平。如今，许多公司依靠用户评论来发布产品。这些评论对公司了解他们的产品在市场上被接受的程度起着重要的作用。但是，今天，一个产品会产生数千条评论。公司必须处理这些评论，以获得用户的意见和想法，这是一个非常繁琐和耗时的过程。本文论述了从用户评论中提取意见是半自动的，从某种意义上说，它需要一定程度的专家协助。在为系统构建领域知识的过程中需要专家的帮助，从而使系统能够学习到该领域的特定词汇。该系统利用领域知识识别和提取给定产品的意见。这些提取的意见包括意见词，它们在权重中的极性，以及这些意见所提供的特征，系统将提取的意见汇总起来以便更好地显示。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2015 International Conference on Technologies for Sustainable Development (ICTSD)

自引率

0.00%

发文量