高级检索
    李勇, 孟小峰, 刘继, 王常青. 基于小数据的在线用户兴趣长程演化研究[J]. 计算机研究与发展, 2015, 52(4): 779-788. DOI: 10.7544/issn1000-1239.2015.20148336
    引用本文: 李勇, 孟小峰, 刘继, 王常青. 基于小数据的在线用户兴趣长程演化研究[J]. 计算机研究与发展, 2015, 52(4): 779-788. DOI: 10.7544/issn1000-1239.2015.20148336
    Li Yong, Meng Xiaofeng, Liu Ji, Wang Changqing. Study of The Long-Range Evolution of Online Human-Interest Based on Small Data[J]. Journal of Computer Research and Development, 2015, 52(4): 779-788. DOI: 10.7544/issn1000-1239.2015.20148336
    Citation: Li Yong, Meng Xiaofeng, Liu Ji, Wang Changqing. Study of The Long-Range Evolution of Online Human-Interest Based on Small Data[J]. Journal of Computer Research and Development, 2015, 52(4): 779-788. DOI: 10.7544/issn1000-1239.2015.20148336

    基于小数据的在线用户兴趣长程演化研究

    Study of The Long-Range Evolution of Online Human-Interest Based on Small Data

    • 摘要: 网络大数据中与Web用户行为相关的数据,例如在线点击数据和通讯记录等,为人们深度挖掘和定量分析人类兴趣动力学带来了机遇,这些在线行为数据被称为大数据时代的“小数据”,有助于揭示许多复杂的人类社会与经济现象.Web用户行为建模时常见的前提假设就是人的行为符合Markov过程,用户下一行为仅依赖于当前行为,与过去的历史行为无关.然而,在线用户行为是一个复杂过程,常常依赖于人的兴趣,对于人类兴趣动力学的本质规律目前知之甚少.利用中国互联网络信息中心提供的30000多名在线用户行为记录数据,基于块熵理论对在线用户行为进行分类研究,通过信息论分析方法,结合熵增曲线的离散导数和积分理论,分析在线用户点击行为的随机性和记忆性特征.研究表明,与常见的假设不同,Web用户的行为并不是一个简单的Markov过程,而是一个符合幂率的非周期无限长程记忆过程;进一步还发现,用户在线连续点击7个兴趣点,其行为的平均预测增益就可达到95.3%以上,可为大数据时代在线用户兴趣精准预测提供理论指导.

       

      Abstract: The availability of network big data, such as those from online human surfing log, e-commerce and communication log, makes it possible to probe into and quantify the dynamics of human-interest. These online behavioral data is called “small data” in the era of big data, which can help explaining many complex socio-economic phenomena. A fundamental assumption of Web user behavioral modeling is that the user’s behavior is consistent with the Markov process and the user’s next behavior only depends on his current behavior regardless of the historical behaviors of the past. However, Web user’s behavior is a complex process and often driven by human interests. We know little about regular pattern of human-interest. In this paper, using more than 30000 online users behavioral log dataset from CNNIC, we explore the use of block entropy as a dynamics classifier for human-interest behaviors. We synthesize several entropy-based approaches to apply information theoretic measures of randomness and memory to the stochastic and deterministic processes of human-interests by using discrete derivatives and integrals of the entropy growth curve. Our results are, however preliminary, that the Web user’s behavior is not a Markov process, but a aperiodic infinitary long-range memory power-law process. Further analysis finds that the predictability gain can exceed 95.3 percent when users click 7 consecutive points online, which can provide theoretical guidance for accurate prediction of online user’s interests in the era of big data.

       

    /

    返回文章
    返回