【摘要】：為了研究網(wǎng)絡(luò)群體中不同情緒對(duì)群體極化的影響,本文從網(wǎng)絡(luò)上已發(fā)生的群體極化現(xiàn)象出發(fā),使用python抓取2016年8月17日到2016年10月8日期間的41496825條微博評(píng)論作為數(shù)據(jù)樣本,并通過(guò)Stanford Word Segmenter進(jìn)行文本分詞,然后使用LIWC進(jìn)行文本分析,進(jìn)而結(jié)合群體極化的測(cè)量方法,建立VAR模型。研究發(fā)現(xiàn):負(fù)向情緒比正向情緒更容易引起網(wǎng)絡(luò)群體極化;相比于悲傷情緒和焦慮情緒,憤怒情緒更容易引起網(wǎng)絡(luò)群體極化。最后,為企業(yè)處理公關(guān)危機(jī)以及政府應(yīng)對(duì)輿論輿情等提供決策建議。
[Abstract]:In order to study the effect of different emotions on group polarization, this paper uses python to capture 41496825 Weibo comments from August 17, 2016 to October 8, 2016 as data samples from the phenomenon of group polarization that has taken place on the network. The text segmentation is carried out by Stanford Word Segmenter, then text analysis is carried out by LIWC, and then the VAR model is established by combining the measurement method of population polarization. It is found that negative emotion is more likely to cause network population polarization than positive emotion, and anger is more likely to cause network population polarization than sadness and anxiety. Finally, for enterprises to deal with public relations crisis and government response to public opinion and other decision-making advice.
【作者單位】： 中南大學(xué)商學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目“SNS環(huán)境中消費(fèi)者如何卷入網(wǎng)絡(luò)團(tuán)購(gòu):群體對(duì)個(gè)體影響的視角”(71272066)
【分類(lèi)號(hào)】：B842.6

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 孫慶洲;韓仁生;;群體極化、不對(duì)稱(chēng)優(yōu)勢(shì)效應(yīng)及風(fēng)險(xiǎn)概率對(duì)風(fēng)險(xiǎn)偏好的影響[J];社會(huì)心理科學(xué);2011年Z2期

相關(guān)重要報(bào)紙文章 前1條

1 編譯 紫萱;從眾心理導(dǎo)致集體盲思[N];北京科技報(bào);2004年

，

本文編號(hào)：2167859