Liang Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Liang Jiang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Lei-Lei Shi
School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu, CN
6 shared publications - John Panneerselvam
Department of Computer Science, University of Exeter, Exeter, England, UK
3 shared publications Lu Liu
University of Leicester,School of Computing and Mathematical Sciences,UK
3 shared publications- Lu Liu
University of Exeter, Exeter, United Kingdom
3 shared publications Jingjing Yao
2 shared publicationsYan Wu
School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang, China
2 shared publications
Latest Publications
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
An Adaptive Community Detection Algorithm based on Density Peaks
Community detection is an important task for analyzing the topological function and structure of a network, as well as for various application scenarios such as advertising, marketing, and influence maximization. Label propagation is a widely used community detection algorithm for complex networks due to its simplicity and fast computation. However, this algorithm has several limitations in terms of stability and the quality of discovered communities. To address these shortcomings, we propose a novel community detection algorithm based on density peaks (ACDDP) in this paper. Firstly, we improve the local density and minimum distance of nodes by using an adaptive selection of community center nodes. Secondly, we specify the node update order to enhance the robustness and performance of the algorithm. The experimental results on real networks demonstrate that our proposed algorithm achieves higher accuracy in community division while ensuring robustness compared to other popular algorithms.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
An Adaptive Community Detection Algorithm based on Density Peaks
Community detection is an important task for analyzing the topological function and structure of a network, as well as for various application scenarios such as advertising, marketing, and influence maximization. Label propagation is a widely used community detection algorithm for complex networks due to its simplicity and fast computation. However, this algorithm has several limitations in terms of stability and the quality of discovered communities. To address these shortcomings, we propose a novel community detection algorithm based on density peaks (ACDDP) in this paper. Firstly, we improve the local density and minimum distance of nodes by using an adaptive selection of community center nodes. Secondly, we specify the node update order to enhance the robustness and performance of the algorithm. The experimental results on real networks demonstrate that our proposed algorithm achieves higher accuracy in community division while ensuring robustness compared to other popular algorithms.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Identifying Influential Communicators based on Correlation and Minimum Distance in Social Media Data Streams
Twitter has become a crucial social networking platform for users to receive and exchange information about current events. Identifying the most influential users in social networks is pivotal for the efficient propagation of information. However, traditional influencer identification models often fall short of assessing users' influence comprehensively and neglect overlapping influence, which greatly restrains their efficiency and accuracy in identifying key users. To address such issues, we propose a method for identifying key users based on correlation and minimum distance (CM-UDM). This method can evaluate users' influence based on their individual, global, local, and propagation path characteristics in social networks. Additionally, we propose a key user decision graph in order to address the problem of overlapping users' influence. We have conducted experiments using one classical dataset and three real Twitter datasets, where the performance of our proposed method in identifying highly influential users is demonstrated.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Identifying Influential Communicators based on Correlation and Minimum Distance in Social Media Data Streams
Twitter has become a crucial social networking platform for users to receive and exchange information about current events. Identifying the most influential users in social networks is pivotal for the efficient propagation of information. However, traditional influencer identification models often fall short of assessing users' influence comprehensively and neglect overlapping influence, which greatly restrains their efficiency and accuracy in identifying key users. To address such issues, we propose a method for identifying key users based on correlation and minimum distance (CM-UDM). This method can evaluate users' influence based on their individual, global, local, and propagation path characteristics in social networks. Additionally, we propose a key user decision graph in order to address the problem of overlapping users' influence. We have conducted experiments using one classical dataset and three real Twitter datasets, where the performance of our proposed method in identifying highly influential users is demonstrated.
- 1 June 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 148, 128-138
A fusion recommendation model based on mutual information and attention learning in heterogeneous social networks
- 1 June 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 148, 128-138
A fusion recommendation model based on mutual information and attention learning in heterogeneous social networks
- 4 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 7 (1) , 141-150
A Social Sensing Model for Event Detection and User Influence Discovering in Social Media Data Streams
Online social networks (OSNs) have emerged as a major platform for sharing information through social relationships and are one of the major sources of big data. Social networks can even accommodate sharing of live streaming data among the connected users. However, social information on social networks is often locally exploited rather than capturing the changes in the entire network over time. Obtaining user's influence statistics is limited only in their local vicinity, which may not facilitate capturing the changes in the user and post influences across the entire network, thereby resulting in lower accuracy while measuring user's topical influence. Moreover, low-influence users always exist in the network publishing low-quality posts. With the objectives of accurately capturing highly influential users and posts, this article proposes a novel dynamic social sensing model, named dynamic PageRank (DPRank) model, to evaluate the dynamic topical influence of the users of social information on social networks during the social information evolution. We deploy our proposed model to real-world Twitter data sets, which demonstrates the effectiveness of our proposed model against notable existing methods while identifying the true influence of users and posts in a dynamically evolving social network.
- 4 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 7 (1) , 141-150
A Social Sensing Model for Event Detection and User Influence Discovering in Social Media Data Streams
Online social networks (OSNs) have emerged as a major platform for sharing information through social relationships and are one of the major sources of big data. Social networks can even accommodate sharing of live streaming data among the connected users. However, social information on social networks is often locally exploited rather than capturing the changes in the entire network over time. Obtaining user's influence statistics is limited only in their local vicinity, which may not facilitate capturing the changes in the user and post influences across the entire network, thereby resulting in lower accuracy while measuring user's topical influence. Moreover, low-influence users always exist in the network publishing low-quality posts. With the objectives of accurately capturing highly influential users and posts, this article proposes a novel dynamic social sensing model, named dynamic PageRank (DPRank) model, to evaluate the dynamic topical influence of the users of social information on social networks during the social information evolution. We deploy our proposed model to real-world Twitter data sets, which demonstrates the effectiveness of our proposed model against notable existing methods while identifying the true influence of users and posts in a dynamically evolving social network.
- 21 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 6 (5) , 1042-1050
Human-Centric Cyber Social Computing Model for Hot-Event Detection and Propagation
Microblogging networks have gained popularity in recent years as a platform enabling expressions of human emotions, through which users can conveniently produce contents on public events, breaking news, and/or products. Subsequently, microblogging networks generate massive amounts of data that carry opinions and mass sentiment on various topics. Herein, microblogging is regarded as a useful platform for detecting and propagating new hot events. It is also a useful channel for identifying high-quality posts, popular topics, key interests, and high-influence users. The existence of noisy data in the traditional social media data streams enforces to focus on human-centric computing. This paper proposes a human-centric social computing (HCSC) model for hot-event detection and propagation in microblogging networks. In the proposed HCSC model, all posts and users are preprocessed through hypertext induced topic search (HITS) for determining high-quality subsets of the users, topics, and posts. Then, a latent Dirichlet allocation (LDA)-based multiprototype user topic detection method is used for identifying users with high influence in the network. Furthermore, an influence maximization is used for final determination of influential users based on the user subsets. Finally, the users mined by influence maximization process are generated as the influential user sets for specific topics. Experimental results prove the superiority of our HCSC model against similar models of hot-event detection and information propagation.
- 21 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 6 (5) , 1042-1050
Human-Centric Cyber Social Computing Model for Hot-Event Detection and Propagation
Microblogging networks have gained popularity in recent years as a platform enabling expressions of human emotions, through which users can conveniently produce contents on public events, breaking news, and/or products. Subsequently, microblogging networks generate massive amounts of data that carry opinions and mass sentiment on various topics. Herein, microblogging is regarded as a useful platform for detecting and propagating new hot events. It is also a useful channel for identifying high-quality posts, popular topics, key interests, and high-influence users. The existence of noisy data in the traditional social media data streams enforces to focus on human-centric computing. This paper proposes a human-centric social computing (HCSC) model for hot-event detection and propagation in microblogging networks. In the proposed HCSC model, all posts and users are preprocessed through hypertext induced topic search (HITS) for determining high-quality subsets of the users, topics, and posts. Then, a latent Dirichlet allocation (LDA)-based multiprototype user topic detection method is used for identifying users with high influence in the network. Furthermore, an influence maximization is used for final determination of influential users based on the user subsets. Finally, the users mined by influence maximization process are generated as the influential user sets for specific topics. Experimental results prove the superiority of our HCSC model against similar models of hot-event detection and information propagation.
- 17 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 6 (6) , 9226-9236
An Efficient Evolutionary User Interest Community Discovery Model in Dynamic Social Networks for Internet of People
Internet of People (IoP), which focuses on personal information collection by a wide range of the mobile applications, is the next frontier for Internet of Things (IoT). Nowadays, people become more and more dependent on the Internet, increasingly receiving and sending information on social networks (e.g., Twitter, etc.); thus social networks play a decisive role in IoP. Therefore, community discovery has emerged as one of the most challenging problems in social networks analysis. To this end, many algorithms have been proposed to detect communities in static networks. However, microblogging social networks are extremely dynamic in both content distribution and topological structure. In this paper, we propose a model EEUICD (Efficient Evolutionary User Interest Community Discovery) which employs a nature-inspired genetic algorithm to improve the quality of community discovery. Specifically, a preprocessing method based on HITS (Hypertext Induced Topic Search) improves the quality of initial users and posts, and a label propagation method is used to restrict the conditions of the mutation process to further improve the efficiency and effectiveness of user interest community detection. Finally, the experiments on the real datasets validate the effectiveness of the proposed model.
- 17 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 6 (6) , 9226-9236
An Efficient Evolutionary User Interest Community Discovery Model in Dynamic Social Networks for Internet of People
Internet of People (IoP), which focuses on personal information collection by a wide range of the mobile applications, is the next frontier for Internet of Things (IoT). Nowadays, people become more and more dependent on the Internet, increasingly receiving and sending information on social networks (e.g., Twitter, etc.); thus social networks play a decisive role in IoP. Therefore, community discovery has emerged as one of the most challenging problems in social networks analysis. To this end, many algorithms have been proposed to detect communities in static networks. However, microblogging social networks are extremely dynamic in both content distribution and topological structure. In this paper, we propose a model EEUICD (Efficient Evolutionary User Interest Community Discovery) which employs a nature-inspired genetic algorithm to improve the quality of community discovery. Specifically, a preprocessing method based on HITS (Hypertext Induced Topic Search) improves the quality of initial users and posts, and a label propagation method is used to restrict the conditions of the mutation process to further improve the efficiency and effectiveness of user interest community detection. Finally, the experiments on the real datasets validate the effectiveness of the proposed model.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1046-1052
Event Detection and Key Posts Discovering in Social Media Data Streams
Microblogging, as a popular social media service, has become a new information channel for users to receive and exchange the most up-to-date information on current events. Consequently, it is crucial to detect new emerging events and to discover the key posts which have the potential to actively disseminate the events through microblogging. However, traditional event detection models require human intervention for detecting the number of topics to be explored, which significantly reduces the efficiency and accuracy of event detection. Most of the existing methods focus only on event detection and are unable to discover the key posts related to the events, making it challenging to track momentous events in timely manner. To tackle these problems, a HITS (Hypertext Induced Topic Search) based topic decision method, named TD-HITS is proposed. TD-HITS can automatically detect the number of topics as well as discovering associated key posts from a large number of posts. The experimental results are based on a Twitter dataset to demonstrate the effectiveness of our proposed methods for both detecting events and identifying key posts.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1046-1052
Event Detection and Key Posts Discovering in Social Media Data Streams
Microblogging, as a popular social media service, has become a new information channel for users to receive and exchange the most up-to-date information on current events. Consequently, it is crucial to detect new emerging events and to discover the key posts which have the potential to actively disseminate the events through microblogging. However, traditional event detection models require human intervention for detecting the number of topics to be explored, which significantly reduces the efficiency and accuracy of event detection. Most of the existing methods focus only on event detection and are unable to discover the key posts related to the events, making it challenging to track momentous events in timely manner. To tackle these problems, a HITS (Hypertext Induced Topic Search) based topic decision method, named TD-HITS is proposed. TD-HITS can automatically detect the number of topics as well as discovering associated key posts from a large number of posts. The experimental results are based on a Twitter dataset to demonstrate the effectiveness of our proposed methods for both detecting events and identifying key posts.