A Social Sensing Model for Event Detection and User Influence Discovering in Social Media Data Streams

Shi, Leilei; Liu, Lu; Wu, Yan; Jiang, Liang; Panneerselvam, John; Crole, Roy L.

doi:10.1109/tcss.2019.2938954

Cited by 29 publications

(28 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we use two popular influence models and their improved versions as our baseline methods, namely HITS-based methods [51] and PageRank-based methods [50], validate the performance of our proposed model.…”

Section: Methodsmentioning

confidence: 98%

“…A HITS based influential user filtering method [13] creates a small high-quality training dataset. A DNS model [50] is used to discover the real dynamic influence of posts, which forms the basis for discovering the real dynamic influence of users and evaluate the dynamic influence of users with various event topics over time. An improved information dissemination model [51] is used to simulate the real information dissemination process by optimizing the IC model.…”

Section: A Ui-ipm Measurementioning

confidence: 99%

“…The dataset is collected from Twitter [50], which is composed of 1,500,000 posts and 36,052 users. As discussed above, to reduce the impact of the bump phenomenon, we only included those users who published or retweeted or replied to posts in our dataset.…”

Section: A Datasetmentioning

confidence: 99%

“…The effectiveness of the proposed UI-IPM method is validated by comparing our proposed model against HITS +DNS+IC [13] and PageRank+DNS+IC [50].…”

Section: B Baseline Approachesmentioning

confidence: 99%

See 3 more Smart Citations

User Topic Preferences Based Influence Maximization in Overlapped Networks

Shi

Liu

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the rapid development of online social networks, there is a trend of information interconnection among online social networks. User's social behaviors are no longer confined to a single network but interact in the form of overlapping networks. Studying the problem of maximizing the influence of overlapping networks can not only make the influence spread to the extent that a single network cannot reach, but also effectively control the cost of advertising while maintaining the scope of diffusion. However, the existing models of user identification and influence propagation in overlapping networks are still not efficient enough. For this reason, this paper studies the problem of maximizing influence in overlapping networks based on user interests. First, network coupling is carried out through the ''bridge'' role of overlapping network users; secondly, independent cascade model is used. On the basis of this, a User Interestbased Influence Propagation Model of the Overlay Network (UI-IPM) is designed. Finally, based on the UI-IPM model, a heuristic algorithm combined with the greedy algorithm is designed to maximize the impact of overlapping networks (UI-IPM) and achieve Influence Maximization of the Overlay Network (IMON) mining seed nodes. The experimental results show the effectiveness of IMON algorithm in terms of influence sphere and time efficiency, and also verify the efficiency of seed nodes mining in overlapping network environment compared with a single network environment.

show abstract

Section: Methodsmentioning

confidence: 98%

Section: A Ui-ipm Measurementioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

“…The effectiveness of the proposed UI-IPM method is validated by comparing our proposed model against HITS +DNS+IC [13] and PageRank+DNS+IC [50].…”

Section: B Baseline Approachesmentioning

confidence: 99%

See 2 more Smart Citations

User Topic Preferences Based Influence Maximization in Overlapped Networks

Shi

Liu

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…These features have made online social networks attract a large number of users who generate a large amount of user generated contents since the day they were born. Therefore, how to use these user generated contents to recommend the information users are interested in and how to continuously optimize the recommendation model for improving the recommendation quality have become one of the hot issues of research [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

et al. 2020

Self Cite

View full text Add to dashboard Cite

The recommendation system is an effective means to solve the information overload problem that exists in social networks, which is also one of the most common applications of big data technology. Thus, the matrix decomposition recommendation model based on scoring data has been extensively studied and applied in recent years, but the data sparsity problem affects the recommendation quality of the model. To this end, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion which makes a personalized recommendation with user-post interaction ratings, implicit feedback and auxiliary information in a hybrid recommendation system. Specifically, the HITS algorithm is used to process the data set, which can filter out the users and posts with high influence and eliminate most of the low-quality users and posts. Secondly, the calculation method of measuring the similarity of candidate posts and the method of calculating K nearest neighbors are designed, which solves the problem that the text description information of post content in the recommendation system is difficult to mine and utilize. Then, the cooperative training strategy is used to achieve the fusion of two recommended views, which eliminates the data distribution deviation added to the training data pool in the iterative training. Finally, the performance of the DMHR algorithm proposed in this paper is compared with other state-of-art algorithms based on the Twitter dataset. The experimental results show that the DMHR algorithm has significant improvements in score prediction and recommendation performance.

show abstract

Topic-based influential user detection: a survey

Panchendrarajan

Saxena

2022

Appl Intell

View full text Add to dashboard Cite

Online Social networks have become an easy means of communication for users to share their opinion on various topics, including breaking news, public events, and products. The content posted by a user can influence or affect other users, and the users who could influence or affect a high number of users are called influential users. Identifying such influential users has a wide range of applications in the field of marketing, including product advertisement, recommendation, and brand evaluation. However, the users’ influence varies in different topics, and hence a tremendous interest has been shown towards identifying topic-based influential users over the past few years. Topic-level information in the content posted by the users can be used in various stages of the topic-based influential user detection (IUD) problem, including data gathering, construction of influence network, quantifying the influence between two users, and analyzing the impact of the detected influential user. This has opened up a wide range of opportunities to utilize the existing techniques to model and analyze the topic-level influence in online social networks. In this paper, we perform a comprehensive study of existing techniques used to infer the topic-based influential users in online social networks. We present a detailed review of these approaches in a taxonomy while highlighting the challenges and limitations associated with each technique. Moreover, we perform a detailed study of different evaluation techniques used in the literature to overcome the challenges that arise in evaluating topic-based IUD approaches. Furthermore, closely related research topics and open research questions in topic-based IUD are discussed to provide a deep understanding of the literature and future directions.

show abstract

A Social Sensing Model for Event Detection and User Influence Discovering in Social Media Data Streams

Cited by 29 publications

References 48 publications

User Topic Preferences Based Influence Maximization in Overlapped Networks

User Topic Preferences Based Influence Maximization in Overlapped Networks

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

Topic-based influential user detection: a survey

Contact Info

Product

Resources

About