本文選題：微博 + 公眾情感狀態(tài)��； 參考：《情報(bào)學(xué)報(bào)》2017年05期

【摘要】：使用社交網(wǎng)絡(luò)數(shù)據(jù)獲取公眾情感,進(jìn)而預(yù)測(cè)新產(chǎn)品市場(chǎng)趨勢(shì)已成為社會(huì)化網(wǎng)絡(luò)環(huán)境下市場(chǎng)信息預(yù)測(cè)研究的新方法。本文研究了基于中文微博情感分析的新產(chǎn)品市場(chǎng)預(yù)測(cè)的相關(guān)問(wèn)題。首先,根據(jù)心理學(xué)的《心境狀態(tài)量表》(POMS),從《同義詞詞林》中提取出七維度心境詞匯種子詞集;利用《同義詞詞林》及word2vec構(gòu)建中文心境狀態(tài)詞匯語(yǔ)義網(wǎng)絡(luò),并通過(guò)馬爾可夫隨機(jī)游走算法計(jì)算詞匯各心境狀態(tài)維度值,自動(dòng)化地構(gòu)建了一個(gè)多維度、細(xì)粒度的情感狀態(tài)詞典,以便獲取微博公眾情感狀態(tài)信息。進(jìn)一步提出一個(gè)整合微博公眾情感狀態(tài)、微博提及數(shù)、評(píng)論情感及其數(shù)量的預(yù)測(cè)特征模型,采用多任務(wù)機(jī)器學(xué)習(xí)方法處理不同提前期的新產(chǎn)品市場(chǎng)預(yù)測(cè)問(wèn)題�；陔娪皵�(shù)據(jù)的實(shí)例分析表明,公眾情感狀態(tài)特征能在更長(zhǎng)的時(shí)段內(nèi)反映新產(chǎn)品市場(chǎng)趨勢(shì),且基于整合的預(yù)測(cè)特征模型和多任務(wù)機(jī)器學(xué)習(xí)方法具有較好的預(yù)測(cè)效力和預(yù)測(cè)提前期。
[Abstract]:It has become a new method to use social network data to obtain public emotion and predict the market trend of new products in the social network environment. This paper studies the market prediction of new products based on Chinese Weibo emotional analysis. First of all, according to the psychological state of mind scale (Poms), we extract the seven dimension mental state vocabulary seed words from synonym forest, and construct the semantic network of Chinese mood state vocabulary by using synonym forest and word2vec. A multi-dimensional, fine-grained emotional state dictionary is automatically constructed by using Markov random walk algorithm to calculate the dimension of mood state of vocabulary, so as to obtain the public emotional state information of Weibo. Furthermore, a forecasting feature model of integrating Weibo's public emotional state with the reference number of Weibo and commenting on emotion and its quantity is put forward, and the multi-task machine learning method is adopted to deal with the market forecasting problem of new products with different lead times. Case study based on film data shows that the characteristics of public emotional state can reflect the trend of new product market in a longer period of time. And the integrated predictive feature model and multitask machine learning method have better prediction effectiveness and prediction lead time.
【作者單位】： 華中師范大學(xué)青少年網(wǎng)絡(luò)心理與行為教育部重點(diǎn)實(shí)驗(yàn)室;賓州大學(xué)神經(jīng)成像中心;華中師范大學(xué)信息管理學(xué)院;孟菲斯大學(xué)智能系統(tǒng)研究所&心理學(xué)系;
【基金】：國(guó)家863計(jì)劃基金項(xiàng)目“基于行為心理動(dòng)力學(xué)模型的群體行為分析與事件態(tài)勢(shì)感知技術(shù)”(2014AA015103) 國(guó)家自然科學(xué)基金項(xiàng)目“基于用戶(hù)偏好感知的SaaS服務(wù)選擇優(yōu)化研究”(71271099),“基于屏幕視覺(jué)熱區(qū)的網(wǎng)絡(luò)用戶(hù)偏好提取及交互式個(gè)性化推薦研究”(71571084)
【分類(lèi)號(hào)】：F274;G206
，

本文編號(hào)：1790878