【摘要】：隨著電子商務(wù)的快速發(fā)展,越來(lái)越多的消費(fèi)者習(xí)慣于網(wǎng)上購(gòu)物。消費(fèi)者在發(fā)生購(gòu)買(mǎi)行為后,可以對(duì)己購(gòu)買(mǎi)的商品進(jìn)行評(píng)論,這些評(píng)論不僅是消費(fèi)者對(duì)商品賣(mài)家的反饋,同時(shí)也能對(duì)其他消費(fèi)者提供建議和指導(dǎo)。商品的熱銷意味著商品評(píng)論的大量增加,某些火爆的商品動(dòng)輒數(shù)萬(wàn)條的評(píng)論讓賣(mài)家和買(mǎi)家都難以處理,這就需要雙方從海量的商品評(píng)論中快速地篩選出有用的評(píng)論,從大量冗余的信息中提取出真正可以指導(dǎo)銷售和購(gòu)買(mǎi)的有用信息。對(duì)海量在線評(píng)論中有用信息的迫切需求使得國(guó)內(nèi)外研究者都不約而同地關(guān)注起了評(píng)論挖掘的一個(gè)具體的應(yīng)用領(lǐng)域——評(píng)論有用性分類。本研究考慮到各大電商網(wǎng)站普遍無(wú)法提供全面的評(píng)論信息這一現(xiàn)實(shí)情況,從評(píng)論內(nèi)容本身及商品特征信息入手,通過(guò)商品特征挖掘?yàn)樵u(píng)論有用性分類特征的選取提供參考；為了充分利用海量的評(píng)論,本研究采用半監(jiān)督學(xué)習(xí)的方法對(duì)分類模型進(jìn)行訓(xùn)練,最終得到有優(yōu)異性能的評(píng)論有用性分類模型。論文首先研究已有商品特征挖掘方法的不足,從分詞、剪枝和特征選取等方面進(jìn)行有效改進(jìn),最后得到優(yōu)化的商品特征挖掘結(jié)果；在此基礎(chǔ)上,深入研究評(píng)論有用性的影響因素,將商品特征信息作為一個(gè)重要參考因素加入到有用性分類特征集合中；最后利用支持向量機(jī)的重要擴(kuò)展——直推式支持向量機(jī)進(jìn)行半監(jiān)督學(xué)習(xí),綜合利用有標(biāo)簽評(píng)論和無(wú)標(biāo)簽評(píng)論,訓(xùn)練出在線評(píng)論有用性的半監(jiān)督分類模型。結(jié)果顯示該分類模型表現(xiàn)優(yōu)于傳統(tǒng)的監(jiān)督學(xué)習(xí)模型,在只考慮評(píng)論內(nèi)容信息條件下有較好的表現(xiàn),進(jìn)而說(shuō)明商品特征信息是影響評(píng)論有用性的重要因素,而半監(jiān)督學(xué)習(xí)可以有效地提升分類結(jié)果。
[Abstract]:With the rapid development of e-commerce, more and more consumers are used to online shopping. After buying, consumers can comment on the goods they buy. These comments are not only feedback from consumers to sellers, but also provide advice and guidance to other consumers. The hot sale of goods means a large increase in commodity reviews. Tens of thousands of comments on some popular goods make it difficult for sellers and buyers to deal with them, which requires both parties to quickly screen useful comments from a large number of commodity reviews and extract useful information from a large number of redundant information that can really guide sales and purchase. The urgent need for useful information in massive online reviews has led researchers at home and abroad to pay attention to a specific application field of comment mining-comment usefulness classification. Considering the fact that major e-commerce websites are generally unable to provide comprehensive comment information, this study provides a reference for the selection of useful classification features through commodity feature mining from the review content itself and commodity feature information. In order to make full use of massive reviews, this study uses semi-supervised learning to train the classification model, and finally obtains a useful review classification model with excellent performance. Firstly, this paper studies the shortcomings of the existing commodity feature mining methods, improves effectively from the aspects of word segmentation, pruning and feature selection, and finally obtains the optimized results of commodity feature mining. On this basis, it deeply studies the influencing factors of the usefulness of the review, and adds the commodity feature information as an important reference factor to the useful classification feature set. Finally, the semi-supervised learning is carried out by using the direct support vector machine, which is an important extension of support vector machine, and the semi-supervised classification model of the usefulness of online comments is trained by using tagged comments and untagged comments. The results show that the classification model is superior to the traditional supervised learning model, and has a better performance under the condition of only considering the content information of the review, which shows that the commodity characteristic information is an important factor affecting the usefulness of the review, and semi-supervised learning can effectively improve the classification results.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：F724.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 苗蕊;;在線評(píng)論有用性研究綜述[J];中國(guó)管理信息化;2014年18期

2 郗亞輝;;產(chǎn)品評(píng)論特征及觀點(diǎn)抽取研究[J];情報(bào)學(xué)報(bào);2014年03期

3 閆強(qiáng);孟躍;;在線評(píng)論的感知有用性影響因素——基于在線影評(píng)的實(shí)證研究[J];中國(guó)管理科學(xué);2013年S1期

4 李宗偉;張艷輝;;體驗(yàn)型產(chǎn)品與搜索型產(chǎn)品在線評(píng)論的差異性分析[J];現(xiàn)代管理科學(xué);2013年08期

5 廖成林;蔡春江;李憶;;電子商務(wù)中在線評(píng)論有用性影響因素實(shí)證研究[J];軟科學(xué);2013年05期

6 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

7 殷國(guó)鵬;劉雯雯;祝珊;;網(wǎng)絡(luò)社區(qū)在線評(píng)論有用性影響模型研究——基于信息采納與社會(huì)網(wǎng)絡(luò)視角[J];圖書(shū)情報(bào)工作;2012年16期

8 嚴(yán)建援;張麗;張蕾;;電子商務(wù)中在線評(píng)論內(nèi)容對(duì)評(píng)論有用性影響的實(shí)證研究[J];情報(bào)科學(xué);2012年05期

9 王平;代寶;;消費(fèi)者在線評(píng)論有用性影響因素實(shí)證研究[J];統(tǒng)計(jì)與決策;2012年02期

10 史偉;王洪偉;;在線產(chǎn)品評(píng)論檢索系統(tǒng)研究[J];情報(bào)雜志;2011年09期

相關(guān)碩士學(xué)位論文 前3條

1 林先杰;在線評(píng)論有用性影響因素研究[D];華南理工大學(xué);2014年

2 金麗君;基于SVM的搜索型商品評(píng)論有用性自動(dòng)識(shí)別方法研究[D];哈爾濱工業(yè)大學(xué);2013年

3 石旭;體驗(yàn)型產(chǎn)品評(píng)論有用性研究[D];華中科技大學(xué);2011年

，

本文編號(hào)：2503059