基于用户行为影响的微博突发话题检测方法

doi:10.3969/j.issn.0253-2778.2017.04.007

摘要/Abstract

摘要： 考虑到微博数据存在时序性特征以及包含用户的社交网络行为特征，提出一种动量信号增强模型算法来有效地检测微博突发话题.由于传统模型未考虑微博数据变化以及用户社交行为的影响，为此首次提出影响力因子以及热度因子，用以修正动量模型.为获取影响力因子，将计算出当前时点前给定周期内的数据对当前数据的变化差值的指数累计影响作为影响力的衡量标准，以体现词频在该区间段的重要性.影响力因子将用于修正词频序列，以获取MACD值指标.由于用户的社交行为对话题产生影响巨大，进而提出热度因子用以修正MACD值指标.当模型满足指标阈值时，特征词则列为突发特征词.最后，通过K-means聚类算法将特征词进行归类合并，以获取突发话题.实验结果表明，模型精度能达到81.82%，表现良好.

关键词: 突发话题, 信号增强, 热度, 影响力, 动量, 聚类

Abstract: Social networks are becoming more and more popular where people can post anything anytime. Due to the huge user community, social network data is increasing with each passing day. Therefore how to explore the knowledge in huge data seems to be hard work. As microblog has time-related characteristics and social network behavior attributes, momentum signal enhancement model is put forward to detect bursty microblog topics effectively. Influence factor and hot energy factor are put forward to improve the momentum model. The influence factor uses the data before the current point but within a given period to calculate the

Key words: bursty topic, momentum, signal enhancement, hot energy； influence

中图分类号:

TP391

万越，隋杰. 基于用户行为影响的微博突发话题检测方法[J]. 中国科学技术大学学报, 2017, 47(4): 328-335.

WAN Yue, SUI Jie. Bursty topic detection method for microblog based on influence from user behaviors[J]. Journal of University of Science and Technology of China, 2017, 47(4): 328-335.

参考文献

［1］
GAGLIO S, RE G L, MORANA M. A framework for real-time Twitter data analysis[J]. Computer Communications, 2016, 73: 236-242.
[2] FUNG G P C, YU J X, YU P S, et al. Parameter free bursty events detection in text streams[C]// Proceedings of the 31st International Conference on Very large Data Bases. Trondheim, Norway: VLDB Endowment, 2005: 181-192.
[3] DIAO Q M, JIANG J, ZHU F D, et al. Finding bursty topics from microblogs[C]// Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Jeju Island, Korea: Association for Computational Linguistics, 2012: 536-544.
[4] 于海峰, 王延章, 卢小丽, 等. 基于知识元的突发事件风险熵预测模型研究[J]. 系统工程学报, 2016, 31(1): 117-126.
YU Haifeng, WANG Yanzhang, LU Xiaoli, et al. Emergency risk entropy forecasting model based on knowledge element[J]. Journal of Systems Engineering, 2016, 31(1): 117-126.
[5] KLEINBERG J. Bursty and hierarchical structure in streams[J]. Data Mining and Knowledge Discovery, 2003, 7(4): 373-397.
[6] CHEN Y, YANG S, CHENG X Q. Bursty topics extraction for web forums[C]// Proceedings of the 11th International Workshop on Web Information and Data Management. Hong Kong, China: ACM Press, 2009: 55-58.
[7] HE D, PARKER D S. Topic momentums: An alternative model of bursts in streams of topics[C]// Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington D C, USA: ACM Press, 2010: 443-452.
[8] 贺敏, 杜攀, 张瑾,等. 基于动量模型的微博突发话题检测方法[J]. 计算机研究与发展, 2015, 52(5): 1022-1028.
HE Min, DU Pan, ZHANG Jin, et al. Microblog bursty topic detection method based on momentum model[J]. Journal of Computer Research and Development, 2015, 52(5): 1022-1028.
[9] HE D, PARKER D S. Learning the funding momentum of research projects[J]. Knowledge Discovery and Data Mining, 2011, 6635(2):532-543.
[10] DU Y, HE Y, TIAN Y, et al. Microblog bursty topic detection based on user relationship[C]// Proceedings of the 6th IEEE Joint International Information Technology and Artificial Intelligence Conference. Chongqing, China: IEEE Press, 2011, 1: 260-263.
[11] 王征, 王林森, 赵磊. 基于信息密度的微博突发话题检测模型研究[J]. 情报理论与实践, 2016, 39(3): 125-129.
[12] 申国伟, 杨武, 王巍,等. 面向大规模微博消息流的突发话题检测[J]. 计算机研究与发展, 2015, 52(2): 512-521.
SHEN Guowei, YANG Wu, WANG Wei, et al. Burst topic detection oriented large-scale microblogs streams[J]. Journal of Computer Research and Development, 2015, 52(2): 512-521.
[13] 贺敏, 徐杰, 杜攀, 等. 基于时间序列分析的微博突发话题检测方法[J]. 通信学报, 2016, 37(3): 48-54.
HE Min, XU Jie, DU Pan, et al. Bursty topic detection method for microblog based on time series analysis[J]. Journal on Communications, 2016, 37(3): 48-54.
[14] 郭跇秀, 吕学强, 李卓. 基于突发词聚类的微博突发事件检测方法[J]. 计算机应用, 2014, 34(2): 486-490, 505.
GUO Yixiu, LYN Xueqiang, LI Zhuo. Bursty topics detection approach on Chinese microblog based on burst words clustering[J]. Journal of Computer Applications, 2014, 34(2): 486-490, 505.
[15] 徐志明, 李栋, 刘挺, 等. 微博用户的相似性度量及其应用[J]. 计算机学报, 2014, 37(1): 207-218.
XU Zhiming, LI Dong, LIU Ting, et al. Measuring similarity between microblog users and its application[J]. Chinese Journal of Computers, 2014, 37(1): 207-218.
[16] 毛佳昕, 刘奕群, 张敏, 等. 基于用户行为的微博用户社会影响力分析[J]. 计算机学报, 2014, 37(4): 791-800.
MAO Jiaxin, LIU Yiqun ZHANG Min, et al. Social influence analysis for micro-blog user based on user behavior[J]. Chinese Journal of Computers, 2014, 37(4): 791-800.
[17] 陈克寒, 韩盼盼, 吴健. 基于用户聚类的异构社交网络推荐算法[J]. 计算机学报, 2013, 36(2): 349-359.
CHEN Kehan, HAN Panpan, WU Jian. User clustering based social network recommendation[J]. Chinese Journal of Computers, 2013, 36(2): 349-359.

（上接第303页）

[8] 余伟, 李石君, 杨莎, 等. Web大数据环境下的不一致跨源数据发现[J]. 计算机研究与发展, 2015, 52(2): 295-308.
YU Wei, LI Shijun, YANG Sha, et al. Automatically discovering of inconsistency among cross-source Data based on Web big Data[J]. Journal of Computer Research and Development, 2015, 52(2): 295-308.
[9] 张安珍,门雪莹,王宏志,等.大数据上基于Hadoop的不一致数据检测与修复算法[J]. 计算机科学与探索, 2015, 9(9): 1044-1055.
[10] 金连,王宏志,黄沈滨,等.基于Map-Reduce的大数据缺失值填充算法[J]. 计算机研究与发展, 2013, 50: 312-321.
[11] 罗元剑,姜建国,王思叶,等.基于有限状态机的RFID流数据过滤与清理技术[J].软件学报, 2014, 25(8): 1713-1728.
LUO Yuanjian, JIANG Jianguo, WANG Siye, et al. Filtering and cleaning for RFID streaming Data technology based on finite state machine[J]. Journal of Software, 2014, 25(8): 1713-1728.
[12] 陈振国，田立勤. 信任模型在雾霾感知源评价中的应用[J].计算机应用, 2016, 36(2): 472-477.
CHEN Zhenguo, TIAN Liqin. Application of trust model in evaluation of haze perception source[J]. Journal of Computer Applications, 2016, 36(2): 472-477.
[13] 罗涛,李俊涛,刘瑞娜,等.VANET中安全信息的快速可靠广播路由算法[J].计算机学报, 2015, 38(3): 663-672.
LUO Tao, LI Juntao, LIU Ruina, et al. A fast and reliable broadcast routing algorithm for safety related information in VANET[J]. Chinese Journal of Computers, 2015, 38(3): 663-672.
[14] 田立勤,林闯, 张琪,等.物联网监测拓扑可靠性设计与优化分析[J].软件学报, 2014, 25(8): 1625-1639.
TIAN Liqin, LIN Chuang, ZHANG Qi, et al. Topology reliability design and optimization analysis of IoT-based monitoring[J]. Journal of Software, 2014, 25(8): 1625-1639.
[15] 钟晓睿,马春光.基于动态累加器的异构传感网认证组密钥管理方案[J]. 通信学报, 2014, 35(3): 124-134.
ZHONG Xiaorui, MA Chunguang. Dynamic accumulators-based authenticated group key management scheme for heterogeneous wireless sensor network[J]. Journal on Communications, 2014, 35(3): 124-134.

[1]	张文静，班志杰. 基于全局的引文网络影响力最大化算法[J]. 中国科学技术大学学报, 2020, 50(8): 1058-1063.
[2]	王悦，李京. 基于可视化的卷积神经网络优化方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 959-967.
[3]	张怿恺，彭勇，孔万增，文益民. 图正则化的模糊局部坐标编码概念分解模型[J]. 中国科学技术大学学报, 2020, 50(7): 993-1002.
[4]	龚乐君，周佘海，程逸飞，高志宏，李华康. 单细胞RNA序列数据的PBMC相关细胞的识别[J]. 中国科学技术大学学报, 2020, 50(7): 1013-1018.
[5]	张玉州，张子为. 基于合作协同进化的多回收站点垃圾收运问题求解[J]. 中国科学技术大学学报, 2020, 50(5): 695-704.
[6]	刘雁，饶元. 基于多领域复杂网络拓扑结构的节点重要度评价方法[J]. 中国科学技术大学学报, 2019, 49(7): 533-543.
[7]	罗彪，刘暄. 基于后向轨迹模式下的合肥市大气污染来源研究[J]. 中国科学技术大学学报, 2019, 49(4): 321-328.
[8]	张滨凯，王翔，郑津津. 结合字典学习和稀疏聚类的医学图像分割算法[J]. 中国科学技术大学学报, 2019, 49(10): 791-796.
[9]	宋云胜，王杰，梁吉业，. 基于数据划分的k-近邻分类加速算法机理分析[J]. 中国科学技术大学学报, 2018, 48(4): 331-340.
[10]	唐风琴，2，丁文文. 基于谱聚类带有节点特征的社区发现算法[J]. 中国科学技术大学学报, 2018, 48(2): 162-173.
[11]	王佳玉，张振宇，褚征，吴晓红. 一种基于轨迹数据密度分区的分布式并行聚类方法[J]. 中国科学技术大学学报, 2018, 48(1): 47-56.
[12]	饶齐，杨燕*，滕飞. 基于多视图加权聚类集成的高速列车工况识别[J]. 中国科学技术大学学报, 2018, 48(1): 35-41.
[13]	徐雪丽，赵学靖. 稀疏谱聚类算法在高维数据上的应用[J]. 中国科学技术大学学报, 2017, 47(4): 311-319.
[14]	罗维佳，乔少杰，韩楠，元昌安，闭应洲，舒红平. 面向LBSN的k-medoids聚类算法[J]. 中国科学技术大学学报, 2017, 47(1): 70-79.
[15]	张辉，赵静. 基于朝向对比度的无监督边界检测算法[J]. 中国科学技术大学学报, 2017, 47(1): 26-31.