来自印尼推特的意见问答

2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA) Pub Date : 2018-11-01 DOI:10.1109/IC3INA.2018.8629516

Wiwin Suwarningsih Nuryani

{"title":"来自印尼推特的意见问答","authors":"Wiwin Suwarningsih Nuryani","doi":"10.1109/IC3INA.2018.8629516","DOIUrl":null,"url":null,"abstract":"One objective of opinion mining is to provide knowledge reasoning from sentences given to the system. It requires an understanding for the meaning of each word including the out-of-vocabulary words and the relation between words in that sentence. Twitter is one of social media networking that allows users to broadcast short text message called tweets. Compared to English, Bahasa Indonesia has a different characteristic on its structure in which it has many words coming from local language that can be categorized as the out-of-vocabulary words. This paper is aimed to explain how to generate the question-answer pairs from opinion statements from Twitter in Bahasa Indonesia. Those generated question-answer pairs will be used to build a question-answer opinion corpus. The proposed approach is the transformation of a pattern-based opinion sentences, focused on the identification of objects, features of objects, and opinions of objects. The final result of this research showed the QA-pairs as a knowledge base for the question and answer opinion system with accuracy reaching 81.7%.","PeriodicalId":179466,"journal":{"name":"2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Opinion QA-Pairs Generation From Indonesian Twitter\",\"authors\":\"Wiwin Suwarningsih Nuryani\",\"doi\":\"10.1109/IC3INA.2018.8629516\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"One objective of opinion mining is to provide knowledge reasoning from sentences given to the system. It requires an understanding for the meaning of each word including the out-of-vocabulary words and the relation between words in that sentence. Twitter is one of social media networking that allows users to broadcast short text message called tweets. Compared to English, Bahasa Indonesia has a different characteristic on its structure in which it has many words coming from local language that can be categorized as the out-of-vocabulary words. This paper is aimed to explain how to generate the question-answer pairs from opinion statements from Twitter in Bahasa Indonesia. Those generated question-answer pairs will be used to build a question-answer opinion corpus. The proposed approach is the transformation of a pattern-based opinion sentences, focused on the identification of objects, features of objects, and opinions of objects. The final result of this research showed the QA-pairs as a knowledge base for the question and answer opinion system with accuracy reaching 81.7%.\",\"PeriodicalId\":179466,\"journal\":{\"name\":\"2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IC3INA.2018.8629516\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IC3INA.2018.8629516","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

意见挖掘的一个目标是从给定的句子中提供知识推理。它需要理解每个单词的意思，包括词汇外的单词和句子中单词之间的关系。Twitter是一种社交媒体网络，允许用户播放被称为tweet的短文本信息。与英语相比，印尼语在结构上有一个不同的特点，印尼语中有许多来自当地语言的词汇，可以归类为词汇外词汇。本文旨在解释如何从印度尼西亚语的Twitter意见声明中生成问答对。这些生成的问答对将用于构建问答意见语料库。提出的方法是基于模式的意见句的转换，重点关注对象的识别、对象的特征和对象的意见。本研究的最终结果表明，问答对作为问答意见系统的知识库，准确率达到81.7%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Opinion QA-Pairs Generation From Indonesian Twitter

One objective of opinion mining is to provide knowledge reasoning from sentences given to the system. It requires an understanding for the meaning of each word including the out-of-vocabulary words and the relation between words in that sentence. Twitter is one of social media networking that allows users to broadcast short text message called tweets. Compared to English, Bahasa Indonesia has a different characteristic on its structure in which it has many words coming from local language that can be categorized as the out-of-vocabulary words. This paper is aimed to explain how to generate the question-answer pairs from opinion statements from Twitter in Bahasa Indonesia. Those generated question-answer pairs will be used to build a question-answer opinion corpus. The proposed approach is the transformation of a pattern-based opinion sentences, focused on the identification of objects, features of objects, and opinions of objects. The final result of this research showed the QA-pairs as a knowledge base for the question and answer opinion system with accuracy reaching 81.7%.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA)

自引率

0.00%

发文量