Time Aware Knowledge Extraction for microblog summarization on Twitter

Microblogging services like Twitter and Facebook collect millions of user generated content every moment about trending news, occurring events, and so on. Nevertheless, it is really a nightmare to find information of interest through the huge amount of available posts that are often noisy and redundant. In the era of Big Data, social media analytics services have caught increasing attention from both research and industry. Specifically, the dynamic context of microblogging requires to manage not only meaning of information but also the evolution of knowledge over the timeline. This work defines Time Aware Knowledge Extraction (briefly TAKE) methodology that relies on temporal extension of Fuzzy Formal Concept Analysis. In particular, a microblog summarization algorithm has been defined filtering the concepts organized by TAKE in a time-dependent hierarchy. The algorithm addresses topic-based summarization on Twitter. Besides considering the timing of the concepts, another distinguishing feature of the proposed microblog summarization framework is the possibility to have more or less detailed summary, according to the user’s needs, with good levels of quality and completeness as highlighted in the experimental results.     

基于微博网络的信息传播模型

微博（Microblog）中信息传播的面积、速度、效率都得到了极大提高,研究信息在微博中的传播规律,对控制和引导舆论具有非常重要的理论价值和现实意义。结合信息在微博网络中的传播规则和微博网络的拓扑结构,通过构建一种新的基于微博网络的信息传播模型,并在实际新浪微博拓扑子网中模拟信息流向,得到如下结论：当信息敏感度大于某一临界值后,明星用户在信息扩散中的意见领袖角色随着信息敏感度的增加而逐渐弱化,当信息敏感度趋于1时,明星用户在信息传播中的优势趋于0。     

基于情感分析的新浪微博争议度分析

随着新浪微博的广泛使用,新浪微博传播的内容涵盖了各种领域的信息,涉及范围越来越广;同时,当用户浏览消息时,不仅能够表达自己的看法,同时能够看到别人的观点。因此,当用户无法判断问题的客观性时,通常会利用其他公众的反馈信息进行评估。为了充分利用公众反馈信息,提出了一种描述公众反馈信息的社会属性——争议度。给出了争议度的概念并构建了争议度计算模型,该模型将公众对微博的反应(即表态、评论、转发等行为)作为争议度的影响因素,通过情感分析等技术计算微博消息的争议度。实验结果对照人工标注结果,模型准确率达到93%,有效率达84%,证明了该模型的可行性。     

Understanding users’ continuous content contribution behaviours on microblogs: an integrated perspective of uses and gratification theory and social influence theory

ABSTRACT

Microblogs are revolutionising the way users produce, consume and distribute short content. The continuous content contributions of users are crucial for the sustainable development of microblogs. Knowledge regarding this user behaviour is scarce. Based on the uses and gratifications theory (U&G) and the social influence theory (SIT), this paper proposes an integrated research model with the aim of understanding the factors that affect users’ continuous content contribution behaviours (CCCB) on microblogs. The data were collected from 379 microblog users in China. The empirical results indicate that perceived gratification had a positive but surprisingly trivial effect on continuous content contribution behaviours. Social influence had a strong and significantly positive effect on users’ CCCB, it also had a positive moderating effect on the relationship between perceived gratification and CCCB. Users’ perceived gratification was positively affected by the antecedents of self-expression, anticipated extrinsic rewards and anticipated reciprocity but negatively affected by privacy concerns. The platform attributes of microblogs (i.e. accessibility and interactivity) also influenced users’ perceived gratification. This research contributes to social media research with regards to the theory of users’ CCCB.     

融合兴趣的微博用户相似度计算研究

针对传统基于用户的博文内容和共同好友数在计算微博用户的相似度时存在潜在误差过大的问题、而基于用户多源背景信息的相似度计算模型有计算复杂度高且忽略了用户的兴趣等问题,提出了一种结合用户兴趣和背景信息的综合相似度计算方法（BIBS）。首先从用户的标签中提取用户的兴趣,当用户的标签缺失时,通过对用户关注关系网络中的重要用户聚类来间接获取用户的兴趣点,以此计算用户的兴趣相似度;其次根据用户的性别、年龄和地点等背景属性计算用户的背景相似度,层次化地挖掘出最相似的用户;最后基于新浪微博的数据进行实验分析。结果表明,与基于多源信息相似度的微博用户推荐算法（MISUR）相比,该方法在用时更少的情况下,准确率、召回率和◢F◣值分别提高了8.1%、16.7%和13.6%,证明了提出的BIBS方法的有效性和准确性。     

微博用户特征量增长规律研究

根据抓取到的新浪微博实际用户数据,分析了粉丝数、关注数和微博数3个特征量的增长模式,发现这3个特征量整体上都随时间线性增长,取整后的增长率服从幂律分布.用户特征量增长模式主要呈持续增长和爆发式增长,其中爆发式增长用户按增长的不同阶段又可以划分为前期、中期、后期和阶跃式4种增长模式.使用基于向量余弦距离相似性的K-means聚类算法,对不同排序和不同初始规模实际用户特征量的时间序列进行聚类分析,统计得到不同增长模式的用户数量.发现用户特征量中增速高的用户增长主要以爆发式增长为主,而规模高的用户增长以持续式增长为主.通过对用户粉丝数爆发式增长的过程分析,对比用户微博被转发和被评论二者的增长关系,提出了导致用户粉丝数爆发式增长的原因.     

面向时间序列的微博话题演化模型研究

话题演化研究有助于追踪用户的喜好和话题的发展趋势,对于舆情预警具有重要意义。目前,话题演化方法注重运用话题生成模型实现话题演化分析,忽略了话题中时间因素和背景词的存在。以传统话题生成模型LDA为基础,将其扩展为微博话题生成模型MTLDA。MTLDA模型增加了对背景词的考虑,提高了话题生成的效率,同时对微博话题集进行时间片划分,利用KL距离计算相邻时间片话题距离,分析话题演化情况。以新浪微博数据为例进行实验,结果表明,MTLDA模型通过时间片划分完成了微博话题的生成,话题演化结果与实际情况吻合。     

基于社会网络分析的微博用户网络结构研究

运用社会网络分析法,以新浪微博特定标签圈下的用户为研究样本,结合用户之间的"关注"与被"关注"关系,构建了用户"相互关注"网络,然后分别从点度中心度、中间中心度和凝聚子群分析等几个方面对该特定网络进行了分析。提出了特定网络的核心用户分析方法,将得到的实验结果与现实数据进行对比,揭示了该特定标签下的核心人物以及网络成员间的关系,实验结果表明该方法对特定网络结构分析具有可行性。最后提出了相应的启示。     

基于mixtureLDA的微博主题挖掘

针对目前的主题挖掘只考虑主题内容的概率分布方法,本文提出一种综合考虑内容、时间等因素的微博主题挖掘模型mixtureLDA. 该模型能够分析用户不同类型微博的主题概率分布和时间微博主题概率. 实验使用新浪微博数据集,结果表明基于mixtureLDA的微博主题挖掘模型能够有效地挖掘出用户微博和时间微博的主题概率分布. 与MB-LDA、userLDA模型对比,mixtureLDA模型可有效降低困惑度.     

Mutual influences between message volume and emotion intensity on emerging infectious diseases: An investigation with microblog data

The dynamic interdependence between microblog volume and emotions expressed in message content has been largely underexplored. To understand the public’s reaction to emerging infectious diseases, we draw upon theories in psychology and social media, and propose that there is a cyclical relationship between message volume and the intensity of emotions (positive or negative) in which they influence each other positively over time. Furthermore, negative and positive emotions mutually suppress each other, yet are autocorrelated, respectively. Relying on more than 560,000 microblogs collected from Sina Weibo between February 2013 and June 2013 on the outbreak of avian influenza in China, we used vector autoregression to test the research model. We find a cyclical relationship between microblog volume and the intensity of negative emotions (fear in particular, a subcategory of negative emotions). Microblog volume positively contributes to positive emotions. While the intensity of negative emotions, and that of positive emotions is autocorrelated, respectively, surprisingly our results suggest that negative emotion intensity positively affects positive emotion intensity. We further rely on impulse response functions to illustrate how the impacts of a variable on another change over time, and generalized forecast error variance decomposition to understand the importance of each variable contributing to the others. Theoretical and practical implications of the study are discussed.