本文選題：情感極性 + 網(wǎng)絡(luò)新聞評(píng)論�。� 參考：《計(jì)算機(jī)工程與應(yīng)用》2017年01期

【摘要】：網(wǎng)絡(luò)新聞評(píng)論情感分析對(duì)于互聯(lián)網(wǎng)時(shí)代分析輿情、掌握民調(diào)具有重要意義。目前研究聚焦在評(píng)論自身的分析而忽略評(píng)論間的結(jié)構(gòu)關(guān)系,因此利用該關(guān)系生成評(píng)論關(guān)系樹,并基于評(píng)論關(guān)系樹建立情感極性判別規(guī)則。將評(píng)論經(jīng)過(guò)預(yù)處理后,同時(shí)采用基于擴(kuò)展情感詞典和支持向量機(jī)兩種方法來(lái)進(jìn)行情感極性分析,動(dòng)態(tài)擴(kuò)展了情感詞典,設(shè)計(jì)了情感極性分類器。實(shí)驗(yàn)結(jié)果表明,在利用了評(píng)論結(jié)構(gòu)關(guān)系之后,兩種方法的分析準(zhǔn)確率均較沒(méi)利用該關(guān)系之前有了明顯的提升。
[Abstract]:The emotional analysis of network news commentary is of great significance for analyzing public opinion and mastering opinion polls in the internet age. At present, the research focuses on the analysis of the commentary itself and neglects the structural relationship between the comments. Therefore, the relationship is used to generate the comment relation tree, and based on the comment relation tree, the rules of judging the emotional polarity are established. After the comments are preprocessed, two methods based on extended emotion dictionary and support vector machine are used to analyze the emotion polarity, the emotion dictionary is dynamically expanded, and the emotion polarity classifier is designed. The experimental results show that the analytical accuracy of the two methods is significantly higher than that of the former.
【作者單位】： 武漢大學(xué)計(jì)算機(jī)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(No.61272109)
【分類號(hào)】：TP391.1
，

本文編號(hào)：1854999