Search

Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network clustering, and link prediction. Most, if not all, of the existing works, are overwhelmingly performed in the context of plain and static networks. Nonetheless, in reality, network structure often evolves over time with addition/deletion of links and nodes. Also, a vast majority of real-world networks are associated with a rich set of node attributes, and their attribute values are also naturally changing, with the emerging of new content patterns and the fading of old content patterns. These changing characteristics motivate us to seek an effective embedding representation to capture network and attribute evolving patterns, which is of fundamental importance for learning in a dynamic environment. To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly. In this paper, we tackle this problem by proposing a novel dynamic attributed network embedding framework - DANE. In particular, DANE first provides an offline method for a consensus embedding and then leverages matrix perturbation theory to maintain the freshness of the end embedding results in an online manner. We perform extensive experiments on both synthetic and real attributed networks to corroborate the effectiveness and efficiency of the proposed framework., Comment: 10 pages

Cyberbullying is a phenomenon which negatively affects the individuals, the victims suffer from various mental issues, ranging from depression, loneliness, anxiety to low self-esteem. In parallel with the pervasive use of social media, cyberbullying is becoming more and more prevalent. Traditional mechanisms to fight against cyberbullying include the use of standards and guidelines, human moderators, and blacklists based on the profane words. However, these mechanisms fall short in social media and cannot scale well. Therefore, it is necessary to develop a principled learning framework to automatically detect cyberbullying behaviors. However, it is a challenging task due to short, noisy and unstructured content information and intentional obfuscation of the abusive words or phrases by social media users. Motivated by sociological and psychological findings on bullying behaviors and the correlation with emotions, we propose to leverage sentiment information to detect cyberbullying behaviors in social media by proposing a sentiment informed cyberbullying detection framework. Experimental results on two real-world, publicly available social media datasets show the superiority of the proposed framework. Further studies validate the effectiveness of leveraging sentiment information for cyberbullying detection.

While social media mining continues to be an active area of research, obtaining data for research is a perennial problem. Even more, obtaining unbiased data is a challenge for researchers who wish to study human behavior, and not technical artifacts induced by the sampling algorithm of a social media site. In this work, we evaluate one social media data outlet that gives data to its users in the form of a stream: Twitter's Sample API. We show that in its current form, this API can be poisoned by bots or spammers who wish to promote their content, jeopardizing the credibility of the data collected through this API. We design a proof-of-concept algorithm that shows how malicious users could increase the probability of their content appearing in the Sample API, thus biasing the content towards spam and bot content and harming the representativity of this data outlet.

Social networking or social media sites are involvedin our daily life. With the increasing popularity of socialmedia sites like Twitter and Facebook, people are using theirsocial network to find answers to their questions. Not everysocial media site can answer a user's question. Different socialmedia sites have different strength such as the StackOverflowcommunity has specific interest in programming and softwaredevelopment, whereas the TripAdvisor community has specificinterest in topic of Travel. Hence, we need a framework toidentify social media sites, which can best answer user's questions. In this paper, we demonstrate system named SocialAnswer which can rank social media sites for user's querybased on the content similarity of social media site and user'squery using ensemble of search engine query results.