Saike He

Identifying peer influence in online social networks using transfer entropy

The past few years have witnessed the rapid growth of online social networks, which have become important hubs of social activity and conduits of information. Identifying social influence in these newly emerging platforms can provide us with significant insights to better understand the interaction behaviors among online users. However, it is difficult for us to measure the influence quantitatively among user peers, since many key factors such as homophily and heterogeneity, can not be observed in our real world conveniently. More recent work mainly focuses on developing theoretical models based on explicit causal knowledge. Nevertheless, such knowledge is usually not available and often needs to be discovered. In this paper, we introduce a model free approach to formulate causal inferences of behaviors among user peers. Experimental results show that influence measured by our approach could successfully reconstruct the underlying networks structure. Furthermore, two additional case studies based on this approach reveal that influentials wield power through specific venues, which constitute a comparatively small portion of the whole channels.

Exploring Entrainment Patterns of Human Emotion in Social Media.

Emotion entrainment, which is generally defined as the synchronous convergence of human emotions, performs many important social functions. However, what the specific mechanisms of emotion entrainment are beyond in-person interactions, and how human emotions evolve under different entrainment patterns in large-scale social communities, are still unknown. In this paper, we aim to examine the massive emotion entrainment patterns and understand the underlying mechanisms in the context of social media. As modeling emotion dynamics on a large scale is often challenging, we elaborate a pragmatic framework to characterize and quantify the entrainment phenomenon. By applying this framework on the datasets from two large-scale social media platforms, we find that the emotions of online users entrain through social networks. We further uncover that online users often form their relations via dual entrainment, while maintain it through single entrainment. Remarkably, the emotions of online users are more convergent in nonreciprocal entrainment. Building on these findings, we develop an entrainment augmented model for emotion prediction. Experimental results suggest that entrainment patterns inform emotion proximity in dyads, and encoding their associations promotes emotion prediction. This work can further help us to understand the underlying dynamic process of large-scale online interactions and make more reasonable decisions regarding emergency situations, epidemic diseases, and political campaigns in cyberspace.

Recursive Deep Learning for Sentiment Analysis over Social Data

Sentiment analysis has now become a popular research problem to tackle in NLP field. However, there are very few researches conducted on sentiment analysis for Chinese. Progress is held back due to lack of large and labelled corpus and powerful models. To remedy this deficiency, we build a Chinese Sentiment Treebank over social data. It concludes 13550 labeled sentences which are from movie reviews. Furthermore, we introduce a novel Recursive Neural Deep Model (RNDM) to predict sentiment label based on recursive deep learning. We consider the problem of classifying one sentence by overall sentiment, determining a review is positive or negative. On predicting sentiment label at sentence level, our model outperforms other commonly used baselines, such as Naïve Bayes, Maximum Entropy and SVM, by a large margin.

A model-free scheme for meme ranking in social media

The prevalence of social media has greatly catalyzed the dissemination and proliferation of online memes (e.g., ideas, topics, melodies, tags, etc.). However, this information abundance is exceeding the capability of online users to consume it. Ranking memes based on their popularities could promote online advertisement and content distribution. Despite such importance, few existing work can solve this problem well. They are either daunted by unpractical assumptions or incapability of characterizing dynamic information. As such, in this paper, we elaborate a model-free scheme to rank online memes in the context of social media. This scheme is capable to characterize the nonlinear interactions of online users, which mark the process of meme diffusion. Empirical studies on two large-scale, real-world datasets (one in English and one in Chinese) demonstrate the effectiveness and robustness of the proposed scheme. In addition, due to its fine-grained modeling of user dynamics, this ranking scheme can also be utilized to explain meme popularity through the lens of social influence.

Parallel Recursive Deep Model for Sentiment Analysis

Sentiment analysis has now become a popular research problem to tackle in Artificial Intelligence (AI) and Natural Language Processing (NLP) field. We introduce a novel Parallel Recursive Deep Model (PRDM) for predicting sentiment label distributions. The main trait of our model is to not only use the composition units, i.e., the vector of word, phrase and sentiment label with them, but also exploit the information encoded among the structure of sentiment label, by introducing a sentiment Recursive Neural Network (sentiment-RNN) together with RNTN. The two parallel neural networks together compose of our novel deep model structure, in which Sentiment-RNN and RNTN cooperate with each other. On predicting sentiment label distributions task, our model outperforms previous state of the art approaches on both full sentences level and phrases level by a large margin.

An Empirical Study of Information Diffusion in Micro-blogging Systems during Emergency Events

Understanding the rapid information diffusion process in social media is critical for crisis management. Most of existing studies mainly focus on information diffusion patterns under the word-of-mouth spread mechanism. However, to date, the mass-media spread mechanism in social media is still not well studied. In this paper, we take the emergency event of Wenzhou train crash as a case and conduct an empirical analysis, utilizing geospatial correlation analysis and social network analysis, to explore the mass-meida spread mechanism in social media. By using the approach of agent-based modeling, we further make a quantativiely comparison with the information diffusion patterns under the word-of-mouth spread mechanism. Our exprimental results show that the mass-meida spread mechanism plays a more important role than that of the word-of-mouth in the information diffusion process during emergency events. The results of this paper can provide significant potential implications for crisis management.

Discovering seasonal patterns of smoking behavior using online search information

Discovering temporal patterns and changes in tobacco use has important practical implications in tobacco control. This paper presents one of the first comprehensive international studies of seasonal smoking patterns based on online searches performed. Using periodogram and cross-correlation, we find that smoking-related search behavior shows strong seasonality effect across countries. In addition, there are significant pairwise associations between such seasonality in different countries.

Topic-oriented information detection and scoring

This paper introduces a new approach for topic-oriented information detection and scoring (TOIDS) based on a hybrid design: integrating characteristic word combination and self learning. Using the characteristic word combination approach, both related and unrelated words are involved to judge a webpages relevance. To address the domain adaptation problem, our self learning technique utilizes historical information from characteristic word lexicon to facilitate detection. Empirical results indicate that the proposed approach outperforms benchmark systems, achieving higher precision. We also demonstrate that our approach can be easily adapted in different domains.

Meme extraction and tracing in crisis events

The proliferation of social media has increased the competition among different memes, which can be free texts, trending catchphrases, or micro media. As human attention is limited, these memes compete with each other, and go in and out of popularity at a rapid pace, sometimes even faster than we can recognize. Popular memes often shape the mindsets of online communities, and also shed light on their future tendencies. Considering the huge volume of memes generated and their continuous mutations, extracting and tracing online memes automatically is rather challenging. In this paper, we propose an automatic meme extraction algorithm. The proposed algorithm extracts massive memes based on phrases independency, and clusters phrase variants of a single meme efficiently. Evaluation on measles outbreak in the USA in 2015 indicates that the proposed algorithm could extract typical memes reflecting the fierce campaign between the pro-vaccination community and the anti-vaccination community. In both communities, memes are power-law distributed, and popular ones have many variants that appear more frequently. By tracing the evolution of online memes, we uncover that popular memes converge and generate peaks at times. Though the pro-vaccination community and the anti-vaccination community may focus on similar memes, they comprehend memes from totally different perspectives and deliver opposing opinions of measles vaccination.

Ranking Online Memes in Emergency Events Based on Transfer Entropy

The rapid proliferation of online social networks has greatly boosted the dissemination and evolution of online memes, which can be free text, trending catchphrase, or micro media. However, this information abundance is exceeding the capability of the public to consume it, especially in unusual situations such as emergency management, intelligence acquisition, and crime analysis. Thus, there calls for a reliable approach to rank meme appropriately according to its influence, which will let the public focus on the most important memes without sinking into the information flood. However, studying meme in any detail on a large scale proves to be challenging. Previous bottom-up approaches are often highly complex, while the more recent top-down network analysis approaches lack detailed modeling for meme dynamics. In this paper, we first present a formal definition for meme ranking task, and then introduce a scheme for meme ranking in the context of online social networks (OSN). To the best of our knowledge, this is the first time that memes have been ranked in a model-free manner. Empirical results on two emergency events indicate that our scheme outperforms several benchmark approaches. This scheme is also robust by insensitive to sample rate. In light of the schemes fine-grain modeling on meme dynamics, we also reveal two key factors affecting meme influence.