本文選題：詞向量 + 情感詞典�。� 參考：《蘭州大學(xué)》2017年碩士論文

【摘要】：文本情感分析,又被叫做情感極性計(jì)算,主要包括意見抽取,意見挖掘,情感挖掘,主客觀分析等研究方向,旨在對(duì)含有人類主觀性態(tài)度的文本數(shù)據(jù)進(jìn)行分析,抽取,挖掘以研究用戶對(duì)篇章級(jí),句子級(jí)或詞語級(jí)文本的情感態(tài)度,是近年來文本挖掘領(lǐng)域比較熱門的方向.本文主要研究評(píng)論文本的正負(fù)向情感分類并在真實(shí)評(píng)論數(shù)據(jù)的基礎(chǔ)上進(jìn)行基于細(xì)粒度的意見挖掘.在情感分類方面,目前主要的研究方法有:基于情感詞典匹配的方法,基于機(jī)器學(xué)習(xí)的方法以及基于深度學(xué)習(xí)的方法,本文在前輩研究者提出算法的基礎(chǔ)上進(jìn)行改進(jìn),考察了一種新的基于詞向量和詞典的情感分類算法以優(yōu)化在無標(biāo)注數(shù)據(jù)集訓(xùn)練模型情況下網(wǎng)站評(píng)論數(shù)據(jù)的情感分類效果,并將其與基于機(jī)器學(xué)習(xí)的方法如支持向量機(jī),邏輯回歸,以及基于深度學(xué)習(xí)的方法如卷積神經(jīng)網(wǎng)絡(luò),長(zhǎng)短期記憶網(wǎng)絡(luò)進(jìn)行比較,分析不同模型方法的優(yōu)劣并提出在實(shí)際應(yīng)用中的可行性建議.在基于細(xì)粒度的意見挖掘方面,我們的主要目的是進(jìn)行基于細(xì)粒度的詞對(duì)(屬性詞,評(píng)價(jià)詞)抽取以收集并分析用戶對(duì)產(chǎn)品不同特征屬性的評(píng)價(jià)情況.本文使用的數(shù)據(jù)集為某品牌筆記本電腦真實(shí)評(píng)論數(shù)據(jù),采用基于依存句法分析結(jié)合語法規(guī)則進(jìn)行抽取和篩選的方法,并依據(jù)抽取結(jié)果進(jìn)一步分析細(xì)粒度層面用戶評(píng)論的正負(fù)情感傾向.
[Abstract]:Text emotion analysis, also called affective polarity calculation, mainly includes opinion extraction, opinion mining, emotion mining, subjective and objective analysis and so on.Mining is a hot topic in the field of text mining in recent years to study users' emotional attitudes towards text at text level, sentence level or word level.This paper mainly studies the positive and negative emotion classification of comment text and carries out fine-grained opinion mining based on the real comment data.In the aspect of emotion classification, the main research methods are as follows: based on affective dictionary matching, machine learning and deep learning.A new affective classification algorithm based on word vectors and dictionaries is investigated to optimize the classification effect of website comment data without annotated dataset training model, and it is compared with machine learning-based methods such as support vector machine (SVM).Logical regression, as well as the methods based on deep learning, such as convolution neural network and long-term and short-term memory network, are compared to analyze the merits and demerits of different model methods and put forward some feasible suggestions in practical application.In the aspect of fine-grained opinion mining, our main purpose is to extract word pairs (attribute words, evaluation words) based on fine granularity to collect and analyze users' evaluation of different feature attributes of products.The data set used in this paper is the real comment data of a brand notebook computer, which is extracted and filtered based on dependency syntactic analysis and grammar rules.According to the extraction results, the positive and negative emotional tendency of fine-grained user comments is further analyzed.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.1;F274

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 蔡慧蘋;王麗丹;段書凱;;基于word embedding和CNN的情感分類模型[J];計(jì)算機(jī)應(yīng)用研究;2016年10期

2 李綱;劉廣興;毛進(jìn);葉光輝;;一種基于句法分析的情感標(biāo)簽抽取方法[J];圖書情報(bào)工作;2014年14期

3 殷國(guó)鵬;;消費(fèi)者認(rèn)為怎樣的在線評(píng)論更有用?——社會(huì)性因素的影響效應(yīng)[J];管理世界;2012年12期

4 婁德成;姚天f ;;漢語句子語義極性分析和觀點(diǎn)抽取方法的研究[J];計(jì)算機(jī)應(yīng)用;2006年11期

5 朱嫣嵐;閔錦;周雅倩;黃萱菁;吳立德;;基于HowNet的詞匯語義傾向計(jì)算[J];中文信息學(xué)報(bào);2006年01期

相關(guān)碩士學(xué)位論文 前1條

1 王文然;基于依存句法分析的互聯(lián)網(wǎng)細(xì)粒度觀點(diǎn)挖掘研究[D];東北財(cái)經(jīng)大學(xué);2011年

，

本文編號(hào)：1760166