OCTOPUS: An Online Topic-Aware Influence Analysis System for Social Networks

Fan, Jiulun; Qiu, Jing; Li, Yuchen; Meng, Qingfei; Zhang, Dongxiang; Li, Guoliang; Tan, Kian-Lee; Du, Xiaoyong

doi:10.1109/icde.2018.00178

Cited by 18 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing work has considered a variety of social features including metadata features such as the number of followers and followees [9,19], the number of retweets and mentions [8], semantic features such as the topics of a candidate influencer's microposts [32,46], or features derived from user behavioral data such as the activeness of a candidate influencer in online activities [1,19]. In addition to those, several pieces of work consider a specific type of feature, namely the structure of the social network among the influencers and other online users, to improve the accuracy in finding social influencers [13,21,27,30,39,40]. For instance, Tang et al [39,40] propose to find the influencers as the nodes from which the spread of information is maximized.…”

Section: Social Influencer Findingmentioning

confidence: 99%

OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation

Arous

Yang

Khayati

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Finding social influencers is a fundamental task in many online applications ranging from brand marketing to opinion mining. Existing methods heavily rely on the availability of expert labels, whose collection is usually a laborious process even for domain experts. Using open-ended questions, crowdsourcing provides a cost-effective way to find a large number of social influencers in a short time. Individual crowd workers, however, only possess fragmented knowledge that is often of low quality.To tackle those issues, we present OpenCrowd, a unified Bayesian framework that seamlessly incorporates machine learning and crowdsourcing for effectively finding social influencers. To infer a set of influencers, OpenCrowd bootstraps the learning process using a small number of expert labels and then jointly learns a feature-based answer quality model and the reliability of the workers. Model parameters and worker reliability are updated iteratively, allowing their learning processes to benefit from each other until an agreement on the quality of the answers is reached. We derive a principled optimization algorithm based on variational inference with efficient updating rules for learning OpenCrowd parameters. Experimental results on finding social influencers in different domains show that our approach substantially improves the state of the art by 11.5% AUC. Moreover, we empirically show that our approach is particularly useful in finding micro-influencers, who are very directly engaged with smaller audiences. CCS CONCEPTS• Information systems → Crowdsourcing; • Human-centered computing → Social network analysis; • Mathematics of computing → Bayesian computation; • Computing methodologies → Neural networks; Learning latent representations.

show abstract

Section: Social Influencer Findingmentioning

confidence: 99%

OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation

Arous

Yang

Khayati

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

show abstract

“…Social Influence Modeling. Conventional social influence studies can be categorized into pairwise (Goyal, Bonchi, and Lakshmanan 2010;Li et al 2018b), topic-level (Tang et al 2009;Chen et al 2015;Fan et al 2018) and structure-level influence (Zhang et al 2013;Li et al 2017). DeepInf (Qiu et al 2018) is a recently proposed deep learning approach that utilizes graph attention networks (GAT) for micro-level influence prediction.…”

Section: Related Workmentioning

confidence: 99%

Social Influence Does Matter: User Action Prediction for In-Feed Advertising

Wang

Meng

Fan

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Social in-feed advertising delivers ads that seamlessly fit inside a user’s feed, and allows users to engage in social actions (likes or comments) with the ads. Many businesses pay higher attention to “engagement marketing” that maximizes social actions, as social actions can effectively promote brand awareness. This paper studies social action prediction for in-feed advertising. Most existing works overlook the social influence as a user’s action may be affected by her friends’ actions. This paper introduces an end-to-end approach that leverages social influence for action prediction, and focuses on addressing the high sparsity challenge for in-feed ads. We propose to learn influence structure that models who tends to be influenced. We extract a subgraph with the near neighbors a user interacts with, and learn topological features of the subgraph by developing structure-aware graph encoding methods. We also introduce graph attention networks to learn influence dynamics that models how a user is influenced by neighbors’ actions. We conduct extensive experiments on real datasets from the commercial advertising platform of WeChat and a public dataset. The experimental results demonstrate that social influence learned by our approach can significantly boost performance of social action prediction.

show abstract

“…Fan et al [23] developed an online topic-aware social influence analysis system, OCTOPUS, which includes three powerful keyword-based topic-aware influence analysis tools, namely keyword-based influential user discovery, personalized influential keywords suggestion, and interactive influential path exploration. Chen et al [24] also focused on the topic-aware influence maximization task.…”

Section: Related Workmentioning

confidence: 99%

Topic Influence Analysis Based on User Intimacy and Social Circle Difference

Wang²,

2019

IEEE Access

View full text Add to dashboard Cite

Analyzing topical user influence in online social networks is conducive to better advertisement injection, information dissemination, and user behavior analysis. In this paper, we propose a new approach to measure topical user influence in online social networks. Specifically, by comprehensively considering users' social relationships, posting and forwarding behaviors, and posts content, we define two metrics of user intimacy and social circle difference to measure how influential users rank on different topics. The dataset obtained from Sina Weibo is utilized to evaluate the effects of our proposed approach and several comparison methods. Specifically, the advantages of our approach are evaluated from several aspects, including the correlations between influence rankings on different topics, the spread ability of high influential users, and the spread balance of high influential users. The extensive experimental results show that our approach is superior in mining influential users on different topics. Specifically, in our approach, the user influence rankings on different topics are less correlated, the users with high influence rankings achieve higher spread scope, and the higher a user's influence ranking, the more evenly the user's posts being spread among different communities.INDEX TERMS Topical user influence, social circle difference, online social networks, user intimacy.

show abstract

OCTOPUS: An Online Topic-Aware Influence Analysis System for Social Networks

Cited by 18 publications

References 8 publications

OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation

OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation

Social Influence Does Matter: User Action Prediction for In-Feed Advertising

Topic Influence Analysis Based on User Intimacy and Social Circle Difference

Contact Info

Product

Resources

About