【摘要】：【目的】基于網(wǎng)絡(luò)產(chǎn)品評論信息構(gòu)建消費(fèi)者的情感波動分析模型。【方法】該分析模型以文本挖掘技術(shù)理論為基礎(chǔ),運(yùn)用產(chǎn)品評論挖掘技術(shù)和情感分析技術(shù),在情感分析的同時(shí)充分考慮不同類型連詞對句子情感傾向性的影響,并采用相應(yīng)的權(quán)值計(jì)算方法。【結(jié)果】從京東和中關(guān)村在線抓取某款手機(jī)從2013年11月到2015年1月這段時(shí)間內(nèi)產(chǎn)品評論信息并進(jìn)行分析,驗(yàn)證了該模型的有效性。【局限】在分析消費(fèi)者情感波動主要影響因素方面,該分析模型主要考慮相鄰時(shí)間段內(nèi)產(chǎn)品特征詞個(gè)數(shù)的變化以及產(chǎn)品特征詞在評論信息中出現(xiàn)次數(shù)的變化這兩個(gè)維度,其他維度并未涉及�！窘Y(jié)論】該模型有效地分析了消費(fèi)者在一段時(shí)間內(nèi)的情感波動趨勢,以及產(chǎn)生情感波動的因素,能夠?yàn)槠髽I(yè)決策提供一定的參考。
[Abstract]:[objective] to construct a consumer emotion fluctuation analysis model based on product review information. [methods] based on the theory of text mining, the model uses product review mining technology and emotion analysis technology. At the same time of affective analysis, the influence of different types of conjunctions on the affective tendency of sentences is fully considered. Using the corresponding weight calculation method. [results] grab the product comment information from JingDong and Zhongguancun online from November 2013 to January 2015 and analyze it. The validity of the model is verified. [limitations] in terms of analyzing the main influencing factors of consumer emotional fluctuation, The analysis model mainly considers the two dimensions of the number of product feature words in adjacent time periods and the number of product feature words appearing in the comment information. Other dimensions are not involved. [conclusion] this model can effectively analyze the trend of consumer emotion fluctuation in a certain period of time, and the factors that produce emotional fluctuation, which can provide a certain reference for enterprises to make decisions.
【作者單位】： 寧波大學(xué)機(jī)械工程與力學(xué)學(xué)院;
【基金】：浙江省自然科學(xué)基金項(xiàng)目“中小企業(yè)業(yè)務(wù)問題及其解決方案的建模理論與管理方法研究”(項(xiàng)目編號:LY14G010003) 國家星火計(jì)劃項(xiàng)目“農(nóng)業(yè)業(yè)務(wù)問題的大數(shù)據(jù)推薦技術(shù)應(yīng)用與示范”(項(xiàng)目編號:2015GA701011) 國家自然科學(xué)基金項(xiàng)目“面向產(chǎn)業(yè)集群廣義制造系統(tǒng)的知識模塊化機(jī)理研究”(項(xiàng)目編號:71671097)的研究成果之一
【分類號】：TP391.1
，

本文編號：2140607