【摘要】：隨著電子商務(wù)的迅猛發(fā)展,網(wǎng)絡(luò)購(gòu)物已經(jīng)成為當(dāng)下中國(guó)最熱的潮流。消費(fèi)者在進(jìn)行網(wǎng)絡(luò)購(gòu)物的同時(shí),也會(huì)根據(jù)網(wǎng)絡(luò)購(gòu)物過(guò)程的體驗(yàn)和產(chǎn)品使用情況發(fā)表用戶評(píng)論。每一條評(píng)論都是帶有情感色彩的,是用戶一種情緒的表達(dá),或是喜歡、厭惡,或是對(duì)商家的意見(jiàn)和建議,準(zhǔn)確及時(shí)地獲知這些用戶情緒對(duì)商家的經(jīng)營(yíng)決策至關(guān)重要。然而這些用戶評(píng)論數(shù)量巨大且屬非結(jié)構(gòu)化信息,只關(guān)注每一條個(gè)體情緒是沒(méi)有意義的,也是不可操作的。因此,需要將所有用戶評(píng)論綜合起來(lái),研究用戶群體情緒的變化,從而有效地支持商家的經(jīng)營(yíng)決策。本研究主要針對(duì)大型B2C電子商務(wù)網(wǎng)站上用戶評(píng)論進(jìn)行研究,使得這些評(píng)論信息可以有效指導(dǎo)商家的經(jīng)營(yíng)決策,具體研究?jī)?nèi)容如下:(1)文章首先對(duì)用戶評(píng)論數(shù)據(jù)進(jìn)行預(yù)處理,采用關(guān)聯(lián)規(guī)則尋找頻繁項(xiàng)集的方法實(shí)現(xiàn)了產(chǎn)品特征的抽取。根據(jù)已抽取到的產(chǎn)品特征,利用產(chǎn)品特征詞和情感傾向詞的共現(xiàn)關(guān)系實(shí)現(xiàn)了“產(chǎn)品特征—情感傾向”詞對(duì)的抽取。然后,基于模糊數(shù)理論構(gòu)建了情感傾向詞模糊語(yǔ)料庫(kù),計(jì)算出了情感傾向詞的模糊隸屬度函數(shù)和情感極性值。并采用模糊認(rèn)知圖對(duì)“產(chǎn)品特征—情感傾向”詞對(duì)及其情感極性值進(jìn)行了知識(shí)表示,構(gòu)建了“產(chǎn)品特征—情感傾向”綜合分析模型;(2)在此基礎(chǔ)上,利用已經(jīng)抽取到的“產(chǎn)品特征—情感傾向”詞對(duì)及其情感極性值構(gòu)建了源案例庫(kù)�；�于證據(jù)理論對(duì)“產(chǎn)品特征—情感傾向”詞對(duì)進(jìn)行兩兩融合,實(shí)現(xiàn)了群體情緒的識(shí)別,并進(jìn)行了群體情緒識(shí)別實(shí)驗(yàn);(3)最后,文章基于時(shí)間序列實(shí)現(xiàn)了群體情緒的演化研究,追蹤了群體情緒的變化過(guò)程和趨勢(shì),這是本文最大的創(chuàng)新點(diǎn)。并依據(jù)群體情緒演化結(jié)果,指導(dǎo)了商家的經(jīng)營(yíng)決策。本文把群體情緒的概念引入到用戶評(píng)論挖掘中來(lái),并基于時(shí)間序列對(duì)群體情緒的演化過(guò)程進(jìn)行研究,在理論方面能夠進(jìn)一步豐富充實(shí)網(wǎng)絡(luò)用戶評(píng)論領(lǐng)域的研究;在實(shí)踐方面,可以使商家準(zhǔn)確及時(shí)地掌握用戶的需求、喜好及變化趨勢(shì),更加高效的指導(dǎo)商家經(jīng)營(yíng)決策。
[Abstract]:With the rapid development of e-commerce, online shopping has become the hottest trend in China. While shopping online, consumers will also make comments according to the experience of online shopping process and the use of products. Each comment is emotional, it is the expression of a kind of user's emotion, or likes, dislikes, or to the merchant's opinion and suggestion, accurate and timely know these user's emotion is very important to the businessman's management decision. However, these users comment on a large number of unstructured information, focusing on each individual emotion is meaningless, and not operational. Therefore, it is necessary to synthesize all user reviews and study the changes of user group emotions, so as to effectively support business decisions. This research mainly focuses on the user comments on large B2C e-commerce websites, which can effectively guide the business decisions. The specific contents are as follows: (1) the paper preprocesses the user comment data. Product feature extraction is realized by using association rules to find frequent itemsets. According to the extracted product features, the cooccurrence relationship between product feature words and affective predisposition words is used to realize the extraction of "product-affective tendency" word pairs. Then, based on the fuzzy number theory, the fuzzy corpus of affective predisposition words is constructed, and the fuzzy membership function and affective polarity value of affective predisposition words are calculated. The fuzzy cognitive map is used to express the word pair of "product feature-affective propensity" and its affective polarity value, and a comprehensive analysis model of "product feature-affective propensity" is constructed. (2) on this basis, the source case database is constructed by using the extracted word pair of "product character-affective tendency" and its affective polarity value. Based on the evidence theory, this paper combines the word pairs of "product characteristics and affective tendency", realizes the recognition of group emotion, and carries on the experiment of group emotion recognition. (3) finally, based on the time series, this paper realizes the research of the evolution of group emotion, and tracks the changing process and trend of group emotion, which is the most innovative point of this paper. And according to the group emotion evolution result, has guided the merchant's management decision. In this paper, the concept of group emotion is introduced into user comment mining, and the evolution process of group emotion is studied based on time series, which can enrich the research of network user comment field in theory. In practice, the business can accurately and timely grasp the user's needs, preferences and trends, and guide business decisions more efficiently.
【學(xué)位授予單位】：東華大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：F724.6;F713.55

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李玲俐;;數(shù)據(jù)挖掘中分類算法綜述[J];重慶師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年04期

2 郗亞輝;張明;袁方;王煜;;產(chǎn)品評(píng)論挖掘研究綜述[J];山東大學(xué)學(xué)報(bào)(理學(xué)版);2011年05期

3 郭鴻;黃桂敏;周婭;;基于Kademlia的下關(guān)聯(lián)規(guī)則挖掘算法研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年01期

4 張珍珍;董才林;陳增照;何秀玲;;改進(jìn)的結(jié)合密度聚類的SVM快速分類方法[J];計(jì)算機(jī)工程與應(yīng)用;2011年02期

5 郭亞琴;王正群;;一種改進(jìn)的支持向量機(jī)BS-SVM[J];微電子學(xué)與計(jì)算機(jī);2010年06期

6 丁春榮;李龍澍;楊寶華;;基于粗糙集的決策樹(shù)構(gòu)造算法[J];計(jì)算機(jī)工程;2010年11期

7 周法國(guó);王映龍;楊炳儒;宋澤鋒;;非結(jié)構(gòu)化信息抽取關(guān)鍵技術(shù)研究探討[J];計(jì)算機(jī)工程與應(yīng)用;2009年14期

8 武建華;沈均毅;王元元;;一種改進(jìn)的關(guān)聯(lián)分類算法[J];計(jì)算機(jī)工程;2009年09期

9 李實(shí);葉強(qiáng);李一軍;Rob Law;;中文網(wǎng)絡(luò)客戶評(píng)論的產(chǎn)品特征挖掘方法研究[J];管理科學(xué)學(xué)報(bào);2009年02期

10 鄭繼明;俞佳;;基于小波變換和支持向量機(jī)的音頻分類[J];計(jì)算機(jī)工程與應(yīng)用;2009年11期

相關(guān)碩士學(xué)位論文 前1條

1 薛金凱;基于案例推理的海上搜救輔助決策研究[D];大連海事大學(xué);2011年

，

本文編號(hào)：2378295