本文選題：情感傾向 + 文本分類　； 參考：《重慶大學(xué)》2016年碩士論文

【摘要】：在電子商務(wù)蓬勃發(fā)展的網(wǎng)絡(luò)環(huán)境下,越來(lái)越多的關(guān)于商品的主觀性評(píng)論文本出現(xiàn)在各類購(gòu)物網(wǎng)站上。這些評(píng)論文本中包含用戶對(duì)產(chǎn)品各個(gè)方面的情感傾向,如喜歡、討厭等。對(duì)其進(jìn)行情感分析不僅可以幫助商家及時(shí)了解商品的優(yōu)缺點(diǎn),從而改善商品質(zhì)量,而且也能為潛在消費(fèi)者的購(gòu)買決策提供數(shù)據(jù)支持。情感分析技術(shù)能充分利用這些海量的評(píng)論文本,從中挖掘出用戶對(duì)商品的褒貶態(tài)度,越來(lái)越多的研究者涉足到這一領(lǐng)域的研究。情感分析技術(shù)的主要任務(wù)是從給定的文本中標(biāo)注出用戶對(duì)某個(gè)事物所表達(dá)的情感傾向。研究?jī)?nèi)容包括非結(jié)構(gòu)化文本的主客觀內(nèi)容識(shí)別、情感傾向性分類,情感強(qiáng)度等。其涉及到自然語(yǔ)言處理、文本分類、機(jī)器學(xué)習(xí)等多個(gè)研究領(lǐng)域。本文的主要研究重點(diǎn)主要是對(duì)主觀性文本所表達(dá)正向或負(fù)向的情感進(jìn)行分類。本文從商品的屬性出發(fā),提出了基于組合神經(jīng)網(wǎng)絡(luò)的屬性聚類算法,并用該方法對(duì)商品屬性進(jìn)行聚類。隨后提出將評(píng)論文本表示成一個(gè)四維向量的表示方法,并結(jié)合SVM算法來(lái)實(shí)現(xiàn)對(duì)商品評(píng)論的情感分析。針對(duì)商品評(píng)論文本中經(jīng)常出現(xiàn)網(wǎng)絡(luò)情感詞語(yǔ)這一特點(diǎn),本文提出了基于Google的word2vec工具來(lái)構(gòu)建商品評(píng)論情感詞典的方法,并用該方法來(lái)對(duì)評(píng)論文本進(jìn)行情感分析�；诮M合神經(jīng)網(wǎng)絡(luò)的屬性聚類方法綜合考慮了評(píng)論文本中屬性詞與其上下文中詞語(yǔ)的位置關(guān)系,根據(jù)語(yǔ)法和上下文信息來(lái)對(duì)評(píng)論文本中的屬性進(jìn)行聚類。通過(guò)聚類,評(píng)論文本被劃分成若干個(gè)簇,隨后給每個(gè)簇標(biāo)注一個(gè)類別標(biāo)簽。每個(gè)類別標(biāo)簽中的評(píng)論文本都是針對(duì)商品的同一屬性進(jìn)行評(píng)價(jià)的。由于商品評(píng)論文本具有篇幅短小、褒貶情感鮮明等特點(diǎn),本文將評(píng)論文本轉(zhuǎn)換為一個(gè)四維的向量。通過(guò)用網(wǎng)絡(luò)爬蟲獲取的真實(shí)的商品評(píng)論作為數(shù)據(jù)源,將本文提出的方法與常見的幾種特征選擇算法進(jìn)行對(duì)比,用SVM算法對(duì)評(píng)論文本的情感傾向進(jìn)行分類,驗(yàn)證了該方法的準(zhǔn)確性和有效性。通過(guò)對(duì)word2vec工具進(jìn)行訓(xùn)練,構(gòu)建商品評(píng)論情感詞典,然后用該詞典對(duì)評(píng)論文本進(jìn)行情感傾向性分類,實(shí)驗(yàn)證明該方法具有較高的分類準(zhǔn)確率。
[Abstract]:In the booming network environment of electronic commerce, more and more subjective comments on goods appear on various shopping websites. These comments contain the user's emotional tendencies towards all aspects of the product, such as likes, dislikes, etc. Emotional analysis can not only help merchants to understand the advantages and disadvantages of goods in time, thus improve the quality of goods, but also provide data support for potential consumers to make purchase decisions. Emotion analysis technology can make full use of these massive comment texts to dig out the user's praise and demerit attitude to the goods. More and more researchers are involved in the research in this field. The main task of affective analysis is to identify the user's emotional tendency towards something from a given text. The research includes subjective and objective content identification, emotional preference classification, emotional intensity and so on. It involves many research fields, such as natural language processing, text classification, machine learning and so on. The main research focus of this paper is to classify positive or negative emotions expressed in subjective texts. In this paper, an attribute clustering algorithm based on combinatorial neural network is proposed for commodity attributes. Then a representation of comment text as a four-dimensional vector is proposed, and a SVM algorithm is used to realize the emotional analysis of commodity comment. In view of the fact that online emotive words often appear in commodity review texts, this paper proposes a method to construct a commodity comment emotion dictionary based on word2vec, and use this method to analyze the emotion of a comment text. The attribute clustering method based on combinatorial neural network considers the location relationship between attribute words in comment text and the words in its context, and clusters attributes in comment text according to syntax and context information. By clustering, the comment text is divided into several clusters, and then each cluster is labeled with a category label. The comment text in each category label is evaluated against the same attribute of the item. Because the commodity review text has the characteristics of short length and distinct emotions, this paper transforms the comment text into a four-dimensional vector. By using the real commodity comment obtained by the web crawler as the data source, the proposed method is compared with several common feature selection algorithms, and SVM algorithm is used to classify the emotional tendency of the comment text. The accuracy and validity of the method are verified. Through the training of word2vec tools, this paper constructs a commodity comment emotion dictionary, and then classifies the comment text with this dictionary. The experiment shows that this method has a high classification accuracy.
【學(xué)位授予單位】：重慶大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 唐曉麗;白宇;張桂平;蔡?hào)|風(fēng);;一種面向聚類的文本建模方法[J];山西大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年04期

2 肖輝輝;段艷明;;基于屬性值相關(guān)距離的KNN算法的改進(jìn)研究[J];計(jì)算機(jī)科學(xué);2013年S2期

3 楊立公;朱儉;湯世平;;文本情感分析綜述[J];計(jì)算機(jī)應(yīng)用;2013年06期

4 楊源;馬云龍;林鴻飛;;評(píng)論挖掘中產(chǎn)品屬性歸類問(wèn)題研究[J];中文信息學(xué)報(bào);2012年03期

5 劉文;吳陳;;一種新的中文文本分類算法——One Class SVM-KNN算法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2012年05期

6 金濤;;網(wǎng)絡(luò)爬蟲在網(wǎng)頁(yè)信息提取中的應(yīng)用研究[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2012年01期

7 張玉芳;王勇;劉明;熊忠陽(yáng);;新的文本分類特征選擇方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2013年05期

8 張彩琴;袁健;;改進(jìn)的正向最大匹配分詞算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2010年11期

9 張紫瓊;葉強(qiáng);李一軍;;互聯(lián)網(wǎng)商品評(píng)論情感分析研究綜述[J];管理科學(xué)學(xué)報(bào);2010年06期

10 康嵐蘭;董丹丹;;常用特征選擇方法的比較研究[J];電腦知識(shí)與技術(shù);2009年34期

相關(guān)博士學(xué)位論文 前1條

1 施寒瀟;細(xì)粒度情感分析研究[D];蘇州大學(xué);2013年

相關(guān)碩士學(xué)位論文 前4條

1 胡馨云;基于屬性的商品評(píng)論情感挖掘研究[D];華中科技大學(xué);2013年

2 葉升陽(yáng);基于網(wǎng)絡(luò)評(píng)論的傾向性分析研究[D];北京郵電大學(xué);2013年

3 岑松祥;領(lǐng)域無(wú)關(guān)的產(chǎn)品評(píng)論分析研究[D];北京郵電大學(xué);2009年

4 陳建美;中文情感詞匯本體的構(gòu)建及其應(yīng)用[D];大連理工大學(xué);2009年

，

本文編號(hào)：2090966