本文選題：微博 + 信息采集　； 參考：《小型微型計(jì)算機(jī)系統(tǒng)》2013年10期

【摘要】：隨著在線社會(huì)關(guān)系網(wǎng)絡(luò)的迅猛發(fā)展,每天數(shù)以千萬(wàn)計(jì)的人通過發(fā)表、評(píng)論、分享等方式,產(chǎn)生和傳播各類話題.對(duì)在線社會(huì)關(guān)系數(shù)據(jù)的感知與收集、存儲(chǔ)管理、群體行為等進(jìn)行研究,能更好地挖掘和分析社會(huì)關(guān)系網(wǎng)絡(luò).由于微博平臺(tái)的登錄、數(shù)據(jù)顯示與處理等方面與傳統(tǒng)網(wǎng)絡(luò)平臺(tái)有很大差異,傳統(tǒng)網(wǎng)絡(luò)爬蟲不適于對(duì)微博信息的全面抓取.本文采用模擬用戶瀏覽行為方法來(lái)爬取海量微博數(shù)據(jù),通過數(shù)據(jù)包截取與分析等手段獲取相關(guān)信息.實(shí)驗(yàn)結(jié)果表明該方法的有效性.在此基礎(chǔ)上,以收集的微博數(shù)據(jù)為研究對(duì)象,對(duì)群體行為進(jìn)行了分析.
[Abstract]:With the rapid development of online social network, tens of millions of people each day through publishing, comments, sharing and other ways to produce and spread all kinds of topics. Research on the perception and collection, storage management, group behavior of online social relations data can better mining and analysis of social networks. Because of the login of Weibo platform, the data display and processing are very different from the traditional network platform, the traditional web crawler is not suitable for the Weibo information capture. In this paper, simulated user browsing behavior is used to crawl massive Weibo data, and relevant information is obtained by packet interception and analysis. The experimental results show that the method is effective. On this basis, the group behavior was analyzed based on the collected Weibo data.
【作者單位】： 河北科技大學(xué)信息科學(xué)與工程學(xué)院;IBM
【基金】：河北省自然科學(xué)基金項(xiàng)目(F2013208105)資助 河北省科技支撐計(jì)劃項(xiàng)目(12213516D)資助
【分類號(hào)】：TP393.092;TP274.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 樊鵬翼;王暉;姜志宏;李沛;;微博網(wǎng)絡(luò)測(cè)量研究[J];計(jì)算機(jī)研究與發(fā)展;2012年04期

2 王珊;王會(huì)舉;覃雄派;周p，

本文編號(hào)：2015258