【摘要】：針對(duì)現(xiàn)有謠言檢測(cè)方法中存在的數(shù)據(jù)采集困難和謠言檢測(cè)滯后的問題,提出一種基于動(dòng)量模型的突發(fā)話題檢測(cè)和領(lǐng)域?qū)＜野l(fā)現(xiàn)的謠言檢測(cè)方法。該方法借鑒物理學(xué)中的動(dòng)力學(xué)理論對(duì)話題特征進(jìn)行建模,使用特征的動(dòng)力學(xué)物理量描述特征的突發(fā)特性和發(fā)展趨勢(shì),并在對(duì)突發(fā)特征進(jìn)行特征聚合之后提取得到突發(fā)話題;然后,依據(jù)話題與用戶個(gè)人信息的領(lǐng)域相關(guān)性在候選專家池中發(fā)現(xiàn)領(lǐng)域相關(guān)的微博用戶來甄別話題信息的真實(shí)性�；谛吕宋⒉⿺�(shù)據(jù)的實(shí)驗(yàn)結(jié)果表明,相對(duì)于僅基于有監(jiān)督機(jī)器學(xué)習(xí)的微博謠言識(shí)別方法,該方法謠言識(shí)別準(zhǔn)確率提高了13個(gè)百分點(diǎn);相對(duì)于主流人工識(shí)別方法,將最長謠言檢測(cè)用時(shí)縮短至20 h,能夠較好地應(yīng)用于實(shí)際的微博謠言檢測(cè)環(huán)境。
[Abstract]:Aiming at the difficulty of data acquisition and the lag of rumor detection in the existing rumour detection methods, a novel method based on momentum model for burst topic detection and rumor detection by domain experts is proposed. The method uses dynamics theory in physics for reference to model the topic feature, uses the dynamic physical quantity of the feature to describe the burst characteristic and the development trend of the feature, and extracts the burst topic after the feature aggregation of the burst feature. Then, according to the domain relevance of topic and user's personal information, Weibo users are found in the pool of candidate experts to identify the authenticity of topic information. The experimental results based on Sina Weibo data show that the accuracy of this method is improved by 13 percentage points compared with the Weibo rumor recognition method based only on supervised machine learning. Compared with the mainstream manual recognition method, the longest rumour detection time can be shortened to 20 hours, which can be applied to the actual rumors detection environment of Weibo.
【作者單位】： 四川大學(xué)計(jì)算機(jī)學(xué)院;四川大學(xué)網(wǎng)絡(luò)空間安全學(xué)院;
【基金】：四川省教育廳重點(diǎn)資助項(xiàng)目(17ZA0238,17ZA0200) 四川省學(xué)術(shù)和技術(shù)帶頭人培養(yǎng)支持經(jīng)費(fèi)資助項(xiàng)目(2016)~~
【分類號(hào)】：G206;TP393.092

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 goldjack;;加油! CEC![J];軟件;2009年11期

相關(guān)碩士學(xué)位論文 前1條

1 李政博;一種適用于領(lǐng)域?qū)＜业腤EB數(shù)據(jù)提取的方法[D];吉林大學(xué);2009年

，

本文編號(hào)：2420727