本文選題：電商評(píng)論 + 相似度��； 參考：《哈爾濱工業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著電子商務(wù)的迅猛發(fā)展,商城的多樣性,商品種類不斷細(xì)化,物流的便捷性,消費(fèi)者的網(wǎng)絡(luò)購物也越來越頻繁,人們慢慢從傳統(tǒng)的實(shí)體店消費(fèi)模式轉(zhuǎn)移到網(wǎng)絡(luò)購物。消費(fèi)者在購買和使用產(chǎn)品之后,對(duì)商品發(fā)表評(píng)分及評(píng)論,在網(wǎng)絡(luò)上分享自己的使用體驗(yàn)。這些評(píng)論日益增多,呈現(xiàn)信息過載的趨勢(shì),同時(shí)評(píng)論中包含了大量信息,也體現(xiàn)了消費(fèi)者對(duì)產(chǎn)品的評(píng)價(jià)及喜好程度。越來越多的人在做出購買決策前喜歡先到網(wǎng)上參考產(chǎn)品的評(píng)論信息。用戶的評(píng)價(jià)通常包含一個(gè)數(shù)值評(píng)分和一段文本形式的評(píng)論,這些評(píng)論體現(xiàn)了用戶對(duì)產(chǎn)品不同屬性特征的偏好和用戶的情感傾向。隨著購物數(shù)量的增大,評(píng)論信息的數(shù)量也會(huì)不斷增加,如果全部閱讀來幫助決策是十分困難的。電商評(píng)論近幾年也成為研究的熱點(diǎn)。評(píng)論數(shù)量的巨增,導(dǎo)致了信息過載。推薦系統(tǒng)已經(jīng)被電子商務(wù)行業(yè)得到廣泛的使用。在各大電商平臺(tái)的界面都可見到“猜你喜歡”。推薦系統(tǒng)通過提供個(gè)性化的推薦幫助人們克服信息過載的問題,其核心是通過個(gè)性化的算法,利用不同用戶對(duì)于不同商品的評(píng)價(jià)信息,發(fā)現(xiàn)他們的喜好。協(xié)同過濾推薦是目前應(yīng)用廣泛的推薦算法,由于它跟具體的領(lǐng)域相關(guān)性比較弱,所以在電商,新聞,評(píng)論,音樂等行業(yè)取得了比較成功的應(yīng)用。簡(jiǎn)單講就是把和目標(biāo)用戶具有相似喜好的用戶喜歡的商品進(jìn)行推薦。本文主要研究?jī)?nèi)容如下:對(duì)用戶的評(píng)論文本進(jìn)行結(jié)構(gòu)化處理,通過中文分詞進(jìn)行提取特征值,通過對(duì)詞頻進(jìn)行統(tǒng)計(jì),提取傾向詞袋,對(duì)潛在用戶進(jìn)行個(gè)性化推薦。通過對(duì)比對(duì)有共同愛好和基于用戶的協(xié)同過濾推薦算法,使用對(duì)有共同愛好個(gè)性化推薦算法,并對(duì)相似性的計(jì)算進(jìn)行了優(yōu)化,提出了基于綜合相似度的計(jì)算方法,分別從用戶對(duì)商品評(píng)分的相似度,基于情感傾向評(píng)分的相似度,基于標(biāo)簽的相似度三個(gè)方面的綜合相似度進(jìn)行計(jì)算,提出相應(yīng)的推薦公式。實(shí)驗(yàn)根據(jù)綜合相似度與傳統(tǒng)相似度的對(duì)比結(jié)果表明,在量化指標(biāo)的衡量下本文中的算法優(yōu)于傳統(tǒng)相似度計(jì)算方法,改善了推薦的質(zhì)量。
[Abstract]:With the rapid development of electronic commerce, the diversity of shopping malls, the variety of goods, the convenience of logistics, the consumers' online shopping is becoming more and more frequent, and people are slowly moving from the traditional consumption mode of physical stores to online shopping.After purchasing and using the product, consumers rate and comment on the product and share their experience online.These comments are increasing, showing the trend of information overload, while the comments contain a lot of information, and also reflect the degree of consumers' evaluation and preference for products.More and more people prefer to go online to refer to product reviews before making purchase decisions.The user's evaluation usually includes a numerical rating and a textual comment, which reflects the user's preference for the different attributes of the product and the user's emotional tendency.As the amount of shopping increases, so will the number of comments, which can be difficult to read to help make decisions.In recent years, ecommerce reviews have also become the focus of research.The huge increase in the number of comments has led to information overload.Recommendation system has been widely used in e-commerce industry.You can see "guess you like" on the interface of all major ecommerce platforms.Recommendation system provides personalized recommendation to help people overcome the problem of information overload. The core of recommendation system is to find out the preferences of different users through personalized algorithm and using the evaluation information of different users for different products.Collaborative filtering recommendation is a widely used recommendation algorithm. Because of its weak correlation with specific fields, collaborative filtering recommendation has been successfully applied in e-commerce, news, commentary, music and other industries.Simply put, it is to recommend the products that the users like to have similar preferences with the target users.The main contents of this paper are as follows: structured processing of user's comment text, extraction of feature value by Chinese word segmentation, extraction of propensity word bag by statistics of word frequency, individualized recommendation to potential users.By comparing the collaborative filtering recommendation algorithms with common interests and users, using personalized recommendation algorithms with common interests, and optimizing the calculation of similarity, a method based on comprehensive similarity is proposed.This paper calculates the similarity of the user's product score, the similarity based on the emotion tendency score and the similarity based on the label, and puts forward the corresponding recommendation formula.The experimental results show that the proposed algorithm is superior to the traditional similarity calculation method and improves the quality of recommendation.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 扈中凱;鄭小林;吳亞峰;陳德人;;基于用戶評(píng)論挖掘的產(chǎn)品推薦算法[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2013年08期

2 章詩杰;姚儉平;;基于評(píng)論挖掘的新協(xié)同過濾推薦模型[J];科技創(chuàng)新與生產(chǎn)力;2013年03期

3 劉東輝;彭德巍;張暉;;一種基于時(shí)間加權(quán)和用戶特征的協(xié)同過濾算法[J];武漢理工大學(xué)學(xué)報(bào);2012年05期

4 王國(guó)霞;劉賀平;;個(gè)性化推薦系統(tǒng)綜述[J];計(jì)算機(jī)工程與應(yīng)用;2012年07期

5 ;A Collaborative Filtering Recommendation Algorithm Based on Item and Cloud Model[J];Wuhan University Journal of Natural Sciences;2011年01期

6 洪文興;翁洋;朱順痣;李茂青;;垂直電子商務(wù)網(wǎng)站的混合型推薦系統(tǒng)[J];系統(tǒng)工程理論與實(shí)踐;2010年05期

7 樊娜;蔡皖東;趙煜;;基于最大熵模型的觀點(diǎn)句主觀關(guān)系提取[J];計(jì)算機(jī)工程;2010年02期

8 周德懋;李舟軍;;高性能網(wǎng)絡(luò)爬蟲:研究綜述[J];計(jì)算機(jī)科學(xué);2009年08期

9 唐慧豐;譚松波;程學(xué)旗;;基于監(jiān)督學(xué)習(xí)的中文情感分類技術(shù)比較研究[J];中文信息學(xué)報(bào);2007年06期

10 張光衛(wèi);李德毅;李鵬;康建初;陳桂生;;基于云模型的協(xié)同過濾推薦算法[J];軟件學(xué)報(bào);2007年10期

相關(guān)會(huì)議論文 前1條

1 鄒嘉彥;;評(píng)述新聞報(bào)道或文章色彩-正負(fù)兩極性自動(dòng)分類的研究[A];全國(guó)第八屆計(jì)算語言學(xué)聯(lián)合學(xué)術(shù)會(huì)議（JSCL-2005）論文集[C];2005年

相關(guān)博士學(xué)位論文 前2條

1 孫慧峰;基于協(xié)同過濾的個(gè)性化Web推薦[D];北京郵電大學(xué);2012年

2 李榮軍;中文商品評(píng)論傾向性分析研究[D];北京郵電大學(xué);2011年

相關(guān)碩士學(xué)位論文 前2條

1 許景楠;基于評(píng)論和評(píng)分的個(gè)性化推薦算法研究[D];浙江大學(xué);2013年

2 陳曉東;基于情感詞典的中文微博情感傾向分析研究[D];華中科技大學(xué);2012年

，

本文編號(hào)：1764337