HXHan Xu

Han Xu

*This is an algorithmically generated author record based on publicly available information.

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


Han Xu has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Sentiment Diffusion in Online Social Networks: A Survey from the Computational Perspective

    by Han Xu, Minghua Xu, Xianjun Deng, Bang Wang

    With the development of mobile technologies, users can easily access Online social networks (OSNs), consequently, massive contents including personal experiences, observations, or opinions are generated online. These contents are being shared and exchanged in OSNs, which have a significant influence on the minds of people toward politics, societies, economics, and so on. In this case, sentiment diffusion which focuses on how the process of information diffusion in OSNs is affected by sentiments has become an important issue. In this survey, we conduct a comprehensive review of the problem. Specifically, we first present the definition and classification of sentiment, introduce the most advanced computational sentiment analysis techniques, list their applications, and disclose available sentiment analysis resources. Then the main OSN components, functionalities, and structural features applied in modeling social networks are analyzed and summarized. Next, a thorough overview of the information diffusion technologies in OSNs, including graph and non-graph models is made. At last, a systematic and in-depth overview of the current state and issues of research on sentiment diffusion in OSNs is provided. This survey provides the necessary knowledge and new insights for relevant researchers to better understand the research state, remaining challenges, and future directions in this field.


  • Open Access

    VRKG4Rec: Virtual Relational Knowledge Graph for Recommendation

    by Lingyun Lu, Bang Wang, Zizhuo Zhang, Shenghao Liu, Han Xu

    Incorporating knowledge graph as side information has become a new trend in recommendation systems. Recent studies regard items as entities of a knowledge graph and leverage graph neural networks to assist item encoding, yet by considering each relation type independently. However, relation types are often too many and sometimes one relation type involves too few entities. We argue that there may exist some latent relevance among relations in KG. It may not necessary nor effective to consider all relation types for item encoding. In this paper, we propose a VRKG4Rec model (Virtual Relational Knowledge Graphs for Recommendation), which clusters relations with latent relevance to generates virtual relations. Specifically, we first construct virtual relational graphs (VRKGs) by an unsupervised learning scheme. We also design a local weighted smoothing (LWS) mechanism for node encoding on VRKGs, which iteratively updates a node embedding only depending on the node itself and its neighbors, but involve no additional training parameters. LWS mechanism is also employed on a user-item bipartite graph for user representation learning, which utilizes item encodings with virtual relational knowledge to help train user representations. Experiment results on two public datasets validate that our VRKG4Rec model outperforms the state-of-the-art methods. The implementations are available at https://github.com/lulu0913/VRKG4Rec.


  • Enhanced sentiment analysis regarding COVID-19 news from global channels

    by Waseem Ahmad, Bang Wang, Philecia Martin, Minghua Xu, Han Xu

    For a healthy society to exist, it is crucial for the media to focus on disease-related issues so that more people are widely aware of them and reduce health risks. Recently, deep neural networks have become a popular tool for textual sentiment analysis, which can provide valuable insights and real-time monitoring and analysis regarding health issues. In this paper, as part of an effort to develop an effective model that can elicit public sentiment on COVID-19 news, we propose a novel approach Cov-Att-BiLSTM for sentiment analysis of COVID-19 news headlines using deep neural networks. We integrate attention mechanisms, embedding techniques, and semantic level data labeling into the prediction process to enhance the accuracy. To evaluate the proposed approach, we compared it to several deep and machine learning classifiers using various metrics of categorization efficiency and prediction quality, and the experimental results demonstrate its superiority with 0.931 testing accuracy. Furthermore, 73,138 pandemic-related tweets posted on six global channels were analyzed by the proposed approach, which accurately reflects global coverage of COVID-19 news and vaccination.


  • How Does Persuasion Happen? A Novel Bounded Confidence Opinion Dynamics Model Based on Social Judgment Theory

    by Han Xu, Xiao Xiao, Minghua Xu, Bang Wang

    Persuasion exists in every aspect of social life. It is important to understand how persuasion works and how strong it is. In this article, we improve the classic Hegselmann–Krause model, one of the most famous bounded confidence models, and propose a novel opinion dynamics model to explain the process by which persuasion occurs from a systematic perspective. In our model, the concepts of latitudes of acceptance, noncommitment, and rejection from social judgment theory and the cognitive error in the process of persuasion, namely assimilation, are introduced. When people are exchanging their opinions with their neighbors, the opinions in the latitude of acceptance will be assimilated, those in the latitude of noncommitment will keep unchanged, and those in the latitude of rejection will not be considered. Theoretical proofs show that our model will converge to a stable state in a finite time. Numerical results of extensive simulation experiments on four datasets show the performance of the model. Furthermore, real social platform data and global COVID-19 vaccination data are analyzed to verify the effectiveness of the model in the decision-making process.


  • Open Access

    Media Bias and Factors Affecting the Impartiality of News Agencies during COVID-19

    by Minghua Xu, Ziling Luo, Han Xu, Bang Wang

    When COVID-19 was raging around the world, people were more fearful and anxious. In this context, the media should uphold impartiality and shoulder the responsibility of eliminating misinformation. Therefore, our research adopted sentiment analysis technologies to analyze the impartiality of news agencies and analyzed the factors that affect the impartiality of COVID-19-related articles about various countries. The SentiWordNet3.0 and bidirectional encoder representations from transformers (BERT) models were employed to analyze the articles and visualize the data. The following conclusions were redrawn in our research. During the pandemic, articles of some news agencies were not objective; the impartiality of news agencies was related to the reliability of news agencies instead of the bias of news agencies; there were obvious differences in the coverage and positivity of international news agencies to report the performance of COVID-19 prevention and control in different countries.


  • Topics, Sentiments, and Emotions Triggered by COVID-19-Related Tweets from IRAN and Turkey Official News Agencies

    by Waseem Ahmad, Bang Wang, Han Xu, Minghua Xu, Zeng Zeng

    There is no doubt that the COVID-19 epidemic posed the most significant challenge to all governments globally since January 2020. People have to readapt after the epidemic to daily life with the absence of an effective vaccine for a long time. The epidemic has led to society division and uncertainty. With such issues, governments have to take efficient procedures to fight the epidemic. In this paper, we analyze and discuss two official news agencies’ tweets of Iran and Turkey by using sentiment- and semantic analysis-based unsupervised learning approaches. The main topics, sentiments, and emotions that accompanied the agencies’ tweets are identified and compared. The results are analyzed from the perspective of psychology, sociology, and communication.


  • Open Access

    Regulatory role of sorting nexin 5 in protein stability and vesicular targeting of vesicular acetylcholine transporter to synaptic vesicle-like vesicles in PC12 cells

    by Meihen Sun, Xu Han, Fei Chang, Hongfei Xu, Lesley Colgan, Yongjian Liu

    Accurate targeting of vesicular acetylcholine transporter (VAChT) to synaptic vesicles (SVs) is indispensable for efficient cholinergic transmission. Previous studies have suggested that the dileucine motif within the C-terminus of the transporter is sufficient for its targeting to SVs. However, the cytosolic machinery underlying specific regulation of VAChT trafficking and targeting to SVs is still unclear. Here we used the C-terminus of VAChT as a bait in a yeast two-hybrid screen to identify sorting nexin 5 (SNX5) as its novel interacting protein. SNX5 was detected in the SVs enriched LP2 subcellular fraction of rat brain homogenate and showed strong colocalization with VAChT in both brain sections and PC12 cells. Binding assays suggested that the C-terminal domain of VAChT can interact with both BAR and PX domain of SNX5. Depletion of SNX5 enhanced the degradation of VAChT and the process was mediated through the lysosomal pathway. More importantly, we found that, in PC12 cells, the depletion of SNX5 expression significantly decreased the synaptic vesicle-like vesicles (SVLVs) localization of VAChT. Therefore, the results suggest that SNX5 is a novel regulator for both stability and SV targeting of VAChT.


  • A Novel Greedy FluidSpread Algorithm With Equilibrium Temperature for Influence Diffusion in Social Networks

    by Marcelo Toalombo, Bang Wang, Han Xu, Minghua Xu

    Maximizing positive influenced users (MPIU) is one of the most important and classic problems in social networks. In this article, we propose an effective solution to the problem of MPIU with positive top- $k$ influence, namely, Greedy FluidSpread Algorithm with Equilibrium Temperature (GFAET). In this article, the behavior of the users, such as the interactions and relationships of each user, and the content of a topic are modeled to the user interest vector and the topic distribution vector, respectively, to calculate the information acceptance probability. The influence diffusion process in social network is modeled as a fluid dynamics system and the attitude of the user is modeled as the fluid temperature. Newton’s law of cooling and fluid dynamics theory is utilized to obtain a more accurate value of equilibrium temperature. Important users are then greedily selected in this system. Extensive experiments demonstrate that our GFAET significantly outperforms other traditional methods in terms of positive influence spread on both artificially generated and real-trace network datasets.