International Journal of Web Based Communities (18 papers in press)

Regular Issues

• Exploring the impact of COVID-19 Pandemic and Vaccine Dissemination on Airbnb's Popularity and Sentiment on Twitter  
  by Sina Shokoohyar, Vahid Ghomi, Amirsalar Jafari Gorizi, Weimin Liang, Charlie Evert 
  Abstract: This study aims to quantify the sentiment of those discussing Airbnb on Twitter and visualise how this sentiment differed in three main periods: prior to the pandemic (pre-COVID-19), and during the pandemic before vaccines were disseminated (pre-vaccine), and during the pandemic, after vaccines were disseminated (post-vaccine). 344,705 tweets relating to Airbnb are collected. In this study, popularity, and usage analytics, sentiment analytics, voice analytics, and topic mining analytics were utilised. Through exploring the data in these three periods, it is possible to distinguish inverse correlations between the number of COVID-19 cases/deaths as compared to the popularity and positive sentiment of Airbnb-related tweets. Other findings include the topics most mentioned along with Airbnb on Twitter and an illustration of how the
  Keywords: peer-to-peer accommodation; Airbnb; COVID-19 pandemic; voice analytics; topic mining analytics; latent Dirichlet allocation; LDA.
  DOI: 10.1504/IJWBC.2024.10056991
   
  
• The Hidden Impact of Hashtags on Instagram: Navigational Heuristics on Source Trustworthiness  
  by Ye Han, Shuang Wu, Peter Haried 
  Abstract: Hashtags are popular navigability tools in a social media-driven environment. However, social media users have purposely employed a hashtag stuffing strategy, where many unrelated hashtags are added to a post to increase the visibility of the post and drive viewership. The results of the current study suggest a potential negative impact of hashtags on source trustworthiness assessment made by Instagram users through heuristic processing. This research conducted two experimental studies with samples from the overall Instagram population. Study 1 (N = 174) was a 2
  Keywords: hashtags; source trustworthiness; technological heuristics; social media; hashtag stuffing; affordance.
  DOI: 10.1504/IJWBC.2024.10062541
   
  
• The Digital Presence of Law Firms: A Study of Social Media Strategies Employed by Prestigious US Law Firms  
  by Sara García-Moreno, Maria Elena Aramendia-Muneta 
  Abstract: The increasing digitalisation has brought to the fore the importance of building and consolidating the digital presence of law firms on the internet. Through the analysis of different accounts on various social networks (Twitter, LinkedIn, Facebook, Instagram, YouTube, Podcast), we will study the strategy of some of the most prestigious law firms in the USA (DLA Piper, Baker McKenzie, Norton Rose Fulbright, Latham & Watkins and White & Case). This paper aims to deepen existing research on social media strategies, as well as to encourage future analysis of law firms in this area. A general tendency has been observed to show the human side of such firms as well as the different pro bono services they are engaged in. The main conclusions found that Law firms need to develop different strategies for each social network and accurately define the target audience in each network.
  Keywords: social media; law firms; marketing strategy; content; Twitter; LinkedIn; Facebook; Instagram.
  DOI: 10.1504/IJWBC.2024.10064760
   
  
• Does Technology Readiness Influence Sustained Use of Social Media Platform? A Cross-National Comparison  
  by Xinsheng Zhao, SungJoon Yoon 
  Abstract: This study attempts to validate an extended technology readiness and technology acceptance model (TRAM), which embraces an emotional feedback measure (enjoyment) to predict the continuous use of social media platforms. In addition, this study aims to determine the differences in the factors affecting sustained use of social media platform between Chinese and Korean users. The result indicated positive technology readiness having a positive impact on five factors (performance expectancy, effort expectancy, asocial influence, facilitating conditions and enjoyment) that were hypothesised to motivate technology acceptance. In addition, the study found that three technology acceptance motivators (performance expectancy, effort expectancy, and enjoyment significantly affect continuous use intention. Finally, the study found that positive technology readiness exerts greater significant effect on technology acceptance factors for China than Korea.
  Keywords: technology acceptance; social media platform; technology readiness; reuse intention; enjoyment; cross-national difference.
  DOI: 10.1504/IJWBC.2024.10064761
   
  
• The Boardroom's Digital Footprint: Exploring the Impact of Diversity on Web-Based Disclosures  
  by Martin Surya Mulyadi, Yunita Anwar 
  Abstract: This study investigates the influence of board diversity on the extent of web-based corporate disclosures within the top publicly listed corporations in Indonesia and Malaysia. Grounded in media agenda-setting theory and using multiple regression analysis, it reveals a significant but nuanced impact of board diversity on disclosure practices. The study finds that while board nationality diversity negatively impacts web-based disclosures, robust corporate governance can mitigate this effect. Conversely, the diversity of foreign educational backgrounds and board gender diversity does not significantly influence web-based disclosures. These findings underscore the importance of a nuanced understanding of board diversity and its interaction with corporate governance in shaping disclosure practices. The research contributes to corporate web disclosure theory and offers practical insights for corporations seeking to optimise their web-based disclosures.
  Keywords: board diversity; web-based corporate disclosures; media agenda setting theory.
  DOI: 10.1504/IJWBC.2024.10064762
   
  

Special Issue on: Consumer Behaviour in Mobile Commerce and Social Media

• Study on Detection of Impulsive Purchase Behavior of E-commerce Platform Consumers Based on Social Network Media  
  by Bo An 
  Abstract: Studying consumers’ impulsive purchasing behaviour helps to understand their purchasing behaviour and increase sales revenue. Therefore, this article proposes a method for detecting consumer impulse buying behaviour on e-commerce platforms based on social network media. Firstly, collect data on consumer purchasing behaviour; Secondly, preprocess the characteristics of impulse buying behaviour based on the RFM function. Then, considering the polarity and degree of emotional words, calculate impulsive emotion scores based on an emotion dictionary; Finally, use the LSH algorithm to find the nearest neighbour point that matches each user’s emotional needs, and use the input of LOF to find the extreme point, obtaining the detection results of impulse buying behaviour. The results show that the detection recall rate of this method can reach 99.0%, the detection error is only 0.02, and the detection time is only 8.9 seconds. The detection effect of this method is good.
  Keywords: social network media; Impulsive purchasing behaviour; e-commerce platforms; K-nearest neighbour method; LOF method; LSH algorithm.
  DOI: 10.1504/IJWBC.2024.10061785
   
  
• Study on Distributed network anomaly attack detection method based on machine learning  
  by Qiaoyun Chen, Youyou Li 
  Abstract: To overcome the problems of traditional methods such as low detection accuracy, high false alarm rate and long detection time, a distributed network anomaly attack detection method based on machine learning is proposed. Firstly, the local density of network operation data points is estimated by combining the Gaussian kernel and cut-off check, and the network operation data is clustered by the DPCA algorithm. Secondly, through the constructed attack model, abnormal attack characteristics are determined and important features are screened. Finally, the naive Bayes in machine learning is used to determine the attribute characteristics of each category in the clustering results. Match the category attribute feature with the important feature to get the anomaly attack detection result. The experimental results show that the maximum detection accuracy of this method is 98%, the average false alarm rate is 2.64%, and the detection time varies between 0.25 s and 0.68 s.
  Keywords: machine learning; distributed; network abnormality; attack detection; DPCA algorithm; naive Bayes.
  DOI: 10.1504/IJWBC.2024.10061786
   
  
• A Precise sensing method of campus network security situation based on fuzzy clustering algorithm  
  by Ranran Yin, Zhenyu Yang 
  Abstract: To ensure the safe operation of the campus network and improve the sensing accuracy and convergence speed, a precise sensing method for campus network security situations based on a fuzzy clustering algorithm is proposed. Firstly, the constructed element model is used to extract the situation elements, and the situation information is processed through the non-negative matrix decomposition algorithm. Secondly, the Kalman entropy method is used to estimate the security situation of the whole network of the network campus, and the new information on the network security situation is calculated. Finally, according to the characteristics of campus network security situation awareness, the network security situation awareness is realised through a fuzzy clustering algorithm. The experimental results show that the MAPE value and RMSE value of the proposed method are low, and the RMSE value is maintained below 0.15, the convergence speed is fast, and can comprehensively reflect the network security situation.
  Keywords: fuzzy clustering algorithm; campus network; security situation awareness; Kalman filter model; transitive closure.
  DOI: 10.1504/IJWBC.2024.10061787
   
  
• Abnormal Behavior Detection of E-commerce Consumers Based on Improved Hidden Markov Model  
  by Meng Su  
  Abstract: To address the issues of low anomaly detection rate, high false positive rate, and long detection time in traditional methods, an abnormal behaviour detection method for e-commerce consumers based on an improved hidden Markov model is proposed. The Scrapy spider framework is used to collect e-commerce consumer behaviour data, including purchase data, browsing data, search data, and evaluation data. The collected data is processed using an improved K-means algorithm for clustering, with normalisation, missing value imputation, and outlier removal applied to the clustering results. The MOPSO algorithm is used to optimise the parameters of the hidden Markov model, and the processed data is then input into the improved hidden Markov model to output the relevant detection results. Experimental results show that the maximum anomaly detection rate of this method is 96.7%, the maximum false positive rate is 4.7%, and the average detection time is 0.73 s.
  Keywords: improved hidden Markov model; e-commerce consumers; abnormal behaviour detection; Scrapy crawler architecture; improved k-means algorithm; MOPSO algorithm.
  DOI: 10.1504/IJWBC.2024.10062542
   
  
• The Moderating Role of Product Involvement in Virtual Reality-Enhanced Online Immersion: Effects on Internet Consumer Behaviour  
  by Imène Ben Yahia, Salma Ayari 
  Abstract: Despite its importance, the mental imagery process has often been overlooked in research on internet user behaviour. This study explores the effects of immersion in a merchant website enhanced by virtual reality devices on mental imagery, as well as on the intention to buy and revisit. A quantitative study involving 350 internet users highlighted the impact of the immersive online experience on mental imagery and internet user responses. The study also examines the moderating effect of product involvement. The results of an experiment validate the hypotheses and provide valuable managerial recommendations. This research contributes significantly to both academics and professionals.
  Keywords: commercial website; online immersion; mental imagery; virtual reality; product involvement.
  DOI: 10.1504/IJWBC.2025.10066227
   
  

Special Issue on: Research Advances on User Interactions in Social Media Using Data Science Approaches

• Large Scale MicroBlog Location Data Capture Method Based on Dynamic Web Page Parsing  
  by Yu Ji, Huanhuan Liu, Zhenzhen Wang, Rui Sun 
  Abstract: Due to the large scale of data, the deviation coefficient of the captured data is large and the capture efficiency is low. To this end, a large-scale Weibo location data retrieval method based on dynamic web page parsing is proposed. Firstly, based on the source of Weibo location data, artificial neural models and random functions are introduced to calculate the weights of feature data. Next, generate a feature vector table and classifier model, and filter the feature text using the established classification model. Finally, by matching the feature data of Weibo location data between dynamic script sites and web pages, a dynamic script parsing framework for Weibo location data on web pages is constructed, and dynamic web page parsing technology is used to capture Weibo location data. The experimental results show that the proposed method has only a 0.1% error in data capture bias, and the capture efficiency reaches 99%. Therefore, this method can significantly improve the crawling effect of large-scale Weibo location data and has certain feasibility.
  Keywords: dynamic web page parsing; MicroBlog location data; crawling; artificial neuron model; random function; dynamic script site.
  DOI: 10.1504/IJWBC.2025.10063048
   
  
• Dynamic collaborative mining method of user perceived interest points in mobile e-commerce platform  
  by Aihua Mo 
  Abstract: In the process of dynamic collaborative mining of user perceived interest points on mobile e-commerce platforms, due to the lack of effective feature classification, the recall rate of interest point data in dynamic collaborative mining of interest points is low. Therefore, a dynamic collaborative mining method for user perceived interest points on mobile e-commerce platforms is proposed. Firstly, coarse grained features of user perceived interest points are initially extracted through clustering algorithms, and their feature values are further extracted using sequence feature extraction algorithms. Then, a user perceived interest prediction model is constructed, and fitting methods are used to achieve feature classification of user perceived interest points; finally, by designing a dynamic collaborative mining model for user perceived interest points on mobile e-commerce platforms, dynamic collaborative mining is achieved. The experimental results show that the dynamic convergence change of method in this paper interest point data mining is relatively small, and the maximum recall rate is 99%, effectively improving mining performance, thereby providing more accurate and accurate personalised recommendations for mobile e-commerce platforms.
  Keywords: mobile e-commerce platform; perceived points of interest; dynamic collaborative mining; coarse grained characteristics; binary classification model.
  DOI: 10.1504/IJWBC.2025.10063049
   
  

Special Issue on: Research Advances on User Interactions in Social Media Using Data Science Approaches

• Customer Churn Prediction Based on Customer Value and User Evaluation Emotions in Online Marketing  
  by Huanan Mo  
  Abstract: In order to improve the accuracy and usefulness of the churn prediction model, the core elements of the research content were designed to include collecting data on customer purchase behaviour and reviews, quantifying and analysing customer value, analysing customer sentiment in reviews, and combining customer value factors and review sentiment factors in the model. The results of the study show that the model performs best on different indicators, and the area of the main characteristic curve is the largest, which is significantly higher than that of the traditional model. Its hit rate, coverage rate and improvement coefficient also perform well. At the same time, when the sample size increases, the improvement coefficient increases the most, reaching 0.41. In conclusion, the model performs well in customer churn prediction, and it can provide certain reference value for the research field of customer churn prediction.
  Keywords: online marketing; customer value; evaluate emotions; customer churn prediction; CCP; fusion model.
  DOI: 10.1504/IJWBC.2025.10062543
   
  
• Personalized Recommendation Method for Live Streaming E-commerce Products Based on Multimedia Social Networks  
  by Yinyue Wan, Pin Lv 
  Abstract: There are problems in personalised recommendation of live streaming e-commerce products, such as low accuracy in user interest mining and weak user relationship strength. Therefore, a personalised recommendation method for live streaming e-commerce products based on multimedia social networks is proposed. First, the user scoring matrix is divided into two interaction matrices by the matrix decomposition method, and the fixed parameter limit matrix dimension is set, and user interest mining is realised by using Euclidean distance calculation; then, the variance expansion factor is introduced to test the multi-collinearity of the feature, and the contour coefficient is calculated to complete the feature extraction; finally, user interest and feature data are introduced into multimedia social networks to obtain product feature attention, perform personalised matching, and achieve personalised recommendation. The results show that the method proposed in this paper has good user interest mining performance and strong user relationships.
  Keywords: multimedia social network; live streaming e-commerce products; personalised recommendation; interest level; variance inflation factor; attention level.
  DOI: 10.1504/IJWBC.2025.10063050
   
  
• A Supply Chain Risk Identification Method of Foreign Trade E-commerce Enterprises Based on Social Network Analysis  
  by Huilan Wu 
  Abstract: To improve the efficiency and accuracy of supply chain risk identification, a supply chain risk identification method for foreign trade e-commerce enterprises based on social network analysis is studied. Firstly, obtain supply chain risk indicators for foreign trade e-commerce enterprises and use the LLE-PCA method to reduce the dimensionality of the indicators; Then, using social network analysis method, construct a social network model with different risk indicators interconnected; Finally, degree centrality analysis and proximity centrality analysis are used to obtain the variable values of each indicator in the model, achieving the identification of supply chain risks for foreign trade e-commerce enterprises. The experiment shows that the application of this method for risk identification takes 0.25s, with a recognition accuracy of 82%. It has high recognition efficiency and accuracy, and the application effect is good.
  Keywords: Social network analysis; Foreign trade e-commerce enterprises; Supply chain; Risk identification; LLE-PCA; Centrality analysis.
  DOI: 10.1504/IJWBC.2025.10063051
   
  
• False information recognition of social media platforms based on multi-modal feature fusion  
  by Yi Tang, Jiaojun Yi, Feigang Tan 
  Abstract: Traditional social media platforms have low accuracy in identifying false information. Therefore, a method based on multi-modal feature fusion is proposed to recognise false information within social media platforms. This method processes false information data on social media platforms by calculating noise during transmission, and utilises multi-layer management to establish correlations between multi-modal point cloud data. By designing modal grouping and calculating similarity, we integrate information from the three dimensions of time, space, and attributes to supplement the shortcomings of the data. By utilising multi-modal feature fusion algorithms, accurate recognition of false information on social media platforms can be achieved. The experimental results show that using this method can effectively improve the training accuracy of the model and have the ability to resist false data injection attacks, achieving high recognition accuracy.
  Keywords: multi-modal feature fusion; social media platform; false information; recognition methods.
  DOI: 10.1504/IJWBC.2025.10063052
   
  
• A Method for Evaluating Confidence of Social Media Information Based on Time Series Analysis  
  by Qiru Zi, Maojia Hou, Qiang Gao 
  Abstract: In order to improve the accuracy of cross confidence assessment and shorten the time required for confidence assessment, this article proposes a social media information confidence assessment method based on time series analysis. Firstly, determine the evaluation indicators that affect the credibility of social media information; then, quantify the evaluation indicators for the credibility of social media information; finally, a confidence quantitative evaluation function is constructed using time series analysis, and a user information weight allocation matrix is used to configure the weight assignment scheme for each evaluation dimension. By quantitatively calculating the relative importance between various indicators in the comparison criteria layer, the user confidence is finally obtained. The experimental results show that the method proposed in this paper can effectively improve the accuracy and recall of confidence evaluation, with a FI value of 0.9, which verifies the effectiveness of the confidence evaluation method proposed in this paper.
  Keywords: time series analysis; confidence level; social media; user topology information; weight allocation.
  DOI: 10.1504/IJWBC.2025.10063053
   
  
• Study on redundant data dimension reduction algorithm for cloud computing in the Internet of Things environment.  
  by Qiaoyun Chen, Hui Yao 
  Abstract: In order to effectively reduce the dimension of cloud computing redundant data and shorten the time of dimensionality reduction, an algorithm for dimensionality reduction of cloud computing redundant data in the Internet of Things environment is proposed. Firstly, analyze the architecture of the Internet of Things environment, and cluster and collect high-dimensional redundant data of cloud computing in the Internet of Things environment. Secondly, K-L transform is used to compress the redundant data of cloud computing. Finally, the supervised discriminant projection dimensionality reduction algorithm is used to construct the objective function model of redundant data dimensionality reduction to complete the dimensionality reduction of redundant data. The experimental results show that compared with traditional algorithms, the dimensionality reduction effect of our algorithm is higher, the dimension of redundant data is significantly reduced, and the dimensionality reduction time of our algorithm is significantly reduced when the data size is the same
  Keywords: Internet of Things environment; Cloud computing; Redundant data dimensionality reduction; Feature compression.
  DOI: 10.1504/IJWBC.2025.10063054