International Journal of Web Based Communities (17 papers in press)

Regular Issues

• Examining the Role of Perceived Social Benefit and Trust Matter in Sustainability of Online Social Networking Community - Social Exchange Theory Perspective  
  by Soo Il Shin, Kyung Young Lee, Dianne J. Hall 
  Abstract: Based on social exchange theory (SET), the current study examines how perceived social benefit from social networking community (SNC) activities influences community members’ affective commitment to the SNC via satisfaction. Additionally, we investigated how SNC members’ trust defined as securing personal privacy and information in the community moderates the relationships between satisfaction and affective commitment. Analysing survey data collected from Facebook users, our findings reveal that SNC members’ perceived social benefit and trust play salient roles in explaining members’ affective commitment to SNCs. Moreover, trust plays an important role in moderating the relationships between SNC members’ perceptions. The current study contributes to the body of knowledge on social networking, web-based communities and social exchange theory literature. Detailed implications and limitations are discussed.
  Keywords: social exchange theory; SET; affective commitment; satisfaction; social networking community; SNC; trust; Facebook.
  DOI: 10.1504/IJWBC.2022.10044659
   
  
• MEDIATING ROLE OF SOCIAL SUPPORT ON THE RELATIONSHIP BETWEEN SOCIAL COMMERCE CONSTRUCTS AND BUYERS’ TRUST  
  by Priyanka Sharma, Sandeep Singh, Rajni Bala, Shafique Ur Rehman 
  Abstract: The social association of the buyers on the web contributes in shaping the social commerce. This study aims to measure the relationship between social commerce constructs, social support (SS) and perceived trust. The sample of the study was constituted of 289 social networking website users selected from northern India. The information regarding social commerce constructs, trust and intention to buy was collected by applying three standardised scales. Partial least square structural equation modelling (PLS-SEM) was used to analyse the data. The results showed that social commerce constructs had a significant impact on social support, while social support exercised a significant effect on trust. The results also confirmed the partial mediation effect of social support. The tested research model can be utilised in the advancement of brand, new products, co-invention of value for branding, and pre-testing any idea of product development on social networking websites.
  Keywords: social commerce constructs; SCCs; trust; social support; SS; Warp-PLS; social networking website.
  DOI: 10.1504/IJWBC.2022.10044798
   
  
• The More I Open Up, the More You "Like" Me: Self-Disclosure and Intimacy Predict Engagement in Women's Facebook Groups  
  by Dana Weimann Saks, Yaron Ariel, Vered Elishar-Malka 
  Abstract: The current research focuses on two closed Facebook groups founded and operated by women, and targets an exclusively female audience with over 100,000 members in each. By analysing 433 posts from one group (study 1), and 1,070 from another (study 2), this paper identified the relationships between levels of self-disclosure expressed in members’ posts, levels of intimacy regarding the topics discussed, and the scale and nature of engagement with these posts. Findings indicate a positive correlation between self-disclosure in the posts and engagement with the posts. This correlation was evident mainly in personal topics. In this sense, closed women’s groups on Facebook have the power to enrich users’ lives with new opportunities for self-expression, socialisation, and empowerment.
  Keywords: social media; closed Facebook groups; women; self-disclosure; intimacy; engagement.
  DOI: 10.1504/IJWBC.2022.10046956
   
  
• The Use of Online Communities of Practice in the Software Industry: Learnings from Facebook Communities in Sri Lanka  
  by Manoja Weerasekara, Åsa Smedberg 
  Abstract: Online communities of practice (CoPs) for professionals is a growing phenomenon in social networking. Such an online CoP consists of people who share their work-related knowledge, experiences, ideas, and practices using different electronic modes. The study focuses on the potential use of online CoPs for social support among software professionals who need to manage a demanding work-life. Five Facebook (FB) groups comprising software employees were cross-examined qualitatively using thematic analysis. The results revealed how software engineers engaged in different practices and activities to support each other in the communities. It was noted how the group members exerted social support, which is considered a key element in occupational health. The findings provide promising insights into how software professionals collaborate and support each other in cyberspace, which could be further explored to design technology that could foster online communities for software employees who need to manage their occupational stress.
  Keywords: work-support; communities of practice; CoP; online communities; software professionals; FB; social support; empathy; occupational stress.
  DOI: 10.1504/IJWBC.2022.10047191
   
  
• Italian top actors during the Covid-19 infodemic on Twitter  
  by Paola Zola, Guglielmo Cola, Antonio Martella, Maurizio Tesconi 
  Abstract: The COVID-19 pandemic has led to a corresponding infodemic, emphasised by the use of social media as the primary communication channel during lockdowns. This study was aimed at finding the accounts that spread information in Italian on COVID-19, and how such information was propagated in the first Western country to face a lockdown. The presented analysis shows that, besides authoritative news media and institutional accounts, a relevant role was played by actors from the
  Keywords: coronavirus; COVID-19; information disorder; network analysis; retweet cascades; social media; Twitter.
  DOI: 10.1504/IJWBC.2022.10047381
   
  

Special Issue on: Advanced Analysis Technologies for Social Media

• Hot spot extraction method of multimedia network public opinion based on Neural Network  
  by TiAN Mi 
  Abstract: In order to overcome the problems of traditional methods, such as poor accuracy of hotspot extraction and poor information recall rate, this paper proposes a method of hotspot extraction of multimedia network public opinion based on neural network. The hot information of multimedia network public opinion in Weibo database is collected by association rules, and the redundant information of multimedia network public opinion hotspot is denoised. Relief algorithm is used to realise the relevant feature screening of public opinion hot information, and the neural network structure is used to calculate the weight threshold of public opinion words to construct the feature target extraction function of public opinion hotspots, so as to realise the multimedia network public opinion hotspots extraction. The results show that the method presented in this paper can improve the accuracy of hotspot information extraction and reduce the CPU consumption during extraction.
  Keywords: multimedia network public opinion; target extraction function; TF-IDF algorithm; neural network training.
  DOI: 10.1504/IJWBC.2022.10044699
   
  
• Data mining analysis method of consumer behavior characteristics based on social media big data  
  by Tiantian An  
  Abstract: In order to solve the problems of low accuracy, high time and small capacity in the current analysis method of consumer behaviour, this paper proposes a method of mining and analysing consumer behaviour feature databased on big data of social media. The big data of social media is preprocessed, and the feature selection model is established to generate the label of social media big data users; k-means algorithm is used to cluster the consumer behaviour feature data, and the multi-dimensional consumption behaviour feature is extracted to construct the hierarchical model of the consumer behaviour feature data; The non-parametric regression method of k-nearest neighbour is used to mining and analysing the characteristics of consumer behaviour. The experimental results show that the accuracy of the proposed method is 92%, the time of feature analysis is only 14 s, and the data analysis capacity is up to 63 T.
  Keywords: social media; big data; k-means algorithm; k-nearest neighbour non-parametric regression method; characteristics of consumption behaviour; data mining analysis.
  DOI: 10.1504/IJWBC.2022.10044700
   
  
• Social E-commerce Consumer Behavior Prediction Model Based on Hierarchical Polarization Characteristics  
  by Junpeng Chen 
  Abstract: In this paper, a social e-commerce consumer behaviour prediction model based on layered polarisation characteristics is constructed. By consumer characteristics, product characteristics and interaction features three aspects to construct social electricity consumer behaviour prediction index system, with the improved locally linear embedding method for social electricity consumer behaviour predictors of high-dimensional data dimension reduction processing, according to the hierarchical polarisation characteristics, social electricity consumer behaviour prediction index weight calculation, based on the weight coefficient, The prediction model of social e-commerce consumer behaviour is constructed to complete the construction of the prediction model of social e-commerce consumer behaviour based on the characteristics of stratified polarisation. The simulation results show that the established model can predict the consumer behaviour of social e-commerce with high accuracy and short prediction time.
  Keywords: social e-commerce; consumer behaviour; hierarchical polarisation characteristics; predictive model; improved local linear embedding method.
  DOI: 10.1504/IJWBC.2022.10044701
   
  
• SEM and fsQCA Factors Influencing Social Media Users' Anxiety  
  by Xiaoping Liu 
  Abstract: In order to solve the problems of low accuracy in determining the influencing factors of anxiety in traditional social media users, time-consuming analysis and large errors in calculating the weights of influencing factors, a social media user based on search engine marketing (SEM) and ask for qualitative comparative analysis (fsQCA) is proposed. An analysis method of the influencing factors of anxiety. The Higuchi algorithm (fractal dimension algorithm) is used to reduce the dimensionality of the social media user’s anxiety representations to achieve preprocessing. Determine the consistency and coverage of the influencing factors through the fsQCA fuzzy set, and realise the analysis of the influencing factors of social media user anxiety. The experimental results show that the minimum error in calculating the weights of the social media users’ anxiety influencing factors using the proposed method is about 0.51%, and the analysis is relatively time-consuming.
  Keywords: search engine marketing; SEM; fsQCA; social media users; user anxiety; factors affecting the.
  DOI: 10.1504/IJWBC.2022.10047190
   
  
• Study on Personalized web design for user based on visual communication  
  by Baohong XIA 
  Abstract: Traditional web design has the problems of poor visual communication effect and high cost. This paper proposes a personalised web design method based on visual communication. The personalised web requirements of users are analysed, and the personalised feature data is extracted; Histogram is used to enhance the brightness of personalised webpage image, and gamma is used to correct the grey error of personalised webpage. The concept of visual communication is introduced to build a visual communication model of personalised web information. Time domain features of personalised web images are extracted; According to the similarity of webpage information, the content of visual communication webpage information design is selected to complete webpage design. The results show that the effect of this method is good, the shortest time is about 1.5 minutes, and the design cost is low.
  Keywords: visual communication; user personalisation; web design; image enhancement.
  DOI: 10.1504/IJWBC.2022.10047382
   
  
• Early warning method of network public opinion communication crisis based on Feature Mining  
  by Qing Cai 
  Abstract: In order to overcome the problems of large P-R value error, high prediction error, and low recall rate in the process of online public opinion dissemination crisis warning, a feature mining-based online public opinion dissemination crisis warning method is proposed. Through MAP_reduce word segmentation processing technology, the word frequency characteristics of public opinion data are mined and processed. Construct a time series model of public opinion, eliminate data delays, obtain the signal characteristics of the crisis data transmitted by the sensor network public opinion through principal component analysis, and complete crisis warning. The experimental results show that the precision value always maintains a high level with the change of the recall value, the slope of the curve is close to 45
  Keywords: feature mining; network public opinion; communication crisis; early warning.
  DOI: 10.1504/IJWBC.2022.10047383
   
  
• A fast encryption method of social network privacy data based on blockchain  
  by Beixin Zhong, Shi Cheng 
  Abstract: In order to overcome the problems of long encryption time and poor security in traditional social network privacy data encryption methods, this paper proposes a fast encryption method of social network privacy data based on block chain. Firstly, the fuzzy C-means clustering algorithm is used to cluster the privacy data in social network, so as to improve the operability of data and shorten the encryption time. Based on the clustering results, combined with the blockchain structure, the elliptic curve encryption algorithm in the blockchain is used to realise the fast encryption of social network privacy data. The experimental results show that the encryption efficiency and encryption security of the proposed method are improved effectively, and the maximum encryption security coefficient reaches 0.98.
  Keywords: blockchain; social network; privacy data; fast encryption.
  DOI: 10.1504/IJWBC.2022.10047483
   
  
• Network social media information leakage detection based on link state awareness  
  by Qi Ding, Guangming Dai 
  Abstract: Aiming at the problems of low detection accuracy and long detection time in traditional information leakage detection methods, this paper proposes a network social media information leakage detection method based on link state perception. Divide the data stream segments, extract the data features of the divided data stream segments, regard the extracted data features of network social media information as the nodes in the social network link, and obtain the node status information by calculating the loss rate and occupancy rate. The distributed heuristic reasoning method is used to perceive the node state information, and the link state is calculated according to the perception results, and the network social media information leakage detection model is constructed. According to the simulation results, compared with the traditional method, the proposed method has higher accuracy and shorter detection time.
  Keywords: link state awareness; online social media; information leakage; data stream fragment.
  DOI: 10.1504/IJWBC.2022.10047484
   
  
• Abnormal data classification of social media based on support vector machine  
  by Kangyi Wang  
  Abstract: Dataset training is ignored in abnormal data classification of network social media, which leads to large errors in data classification results. This paper proposes a classification method for abnormal data of social media based on support vector machine (SVM). Online social media data through the curvature features be divided into two different regions, and with the aid of data denoising filtering method is different for different area, by using genetic algorithm to improve K means clustering algorithm, through training set to train the SVM classifier for abnormal data, selecting samples closest to the hyperplane as negative samples, and training SVM, Complete the abnormal data classification of network social media. The results show that the proposed method has the highest error rate of about 1.25% in the classification of abnormal data in network social media, and the data classification can be completed in a relatively short time.
  Keywords: support vector machine; SVM; network social media; classification of abnormal data; noise removal and filtering; negative sample.
  DOI: 10.1504/IJWBC.2022.10047485
   
  
• Dynamic encryption method of personal privacy information in social network based on blockchain technology  
  by Feifei Geng, Lu Yu 
  Abstract: In order to overcome the problems of low encryption accuracy, long encryption time and poor encryption effect in traditional methods, a dynamic encryption method of personal privacy information in social networks based on blockchain technology is proposed. Using cryptography encryption method to obtain the personal privacy information of social network, according to homomorphic encryption to obtain the privacy information plaintext to be encrypted, the hash function model is constructed, and the hash value is stored in the blockchain to obtain the personal privacy protection information key. Read the personal privacy information record blockchain, and realise the blind attribute encryption of personal privacy information. The results show that when the amount of information is 500 GB, the data recall rate is up to 99%, the encryption accuracy is up to 99.9%, and the average information entropy is 8.9242, indicating that the proposed method can improve the privacy information encryption effect.
  Keywords: blockchain; cryptography; social network; personal privacy information; information encryption; hash function; homomorphic encryption.
  DOI: 10.1504/IJWBC.2022.10047486
   
  
• Social media image classification and retrieval method based on deep hash algorithm  
  by Zilong Li, Yong Zhou, Hongdong Wang 
  Abstract: In order to solve the problems of large classification error and low retrieval accuracy of traditional retrieval methods, a social media image classification retrieval method based on deep hash algorithm is proposed. With the help of CBOW model to extract semantic features and colour histogram to extract colour features of social media images, social media image classification is completed. Hash algorithm is used to deal with the unidirectional irreversibility of social media image, and the pixel feature points in the image are regarded as density function for one-to-one correspondence. The loss function is used to control the convergence of the hash algorithm to achieve social media image retrieval. Experimental results show that the error of social media image classification is only 2%, the retrieval accuracy is always higher than 90%, and the retrieval time is only 3.4 s, which has the advantage of high retrieval efficiency.
  Keywords: social media images; CBOW model; clustering algorithm; deep hash algorithm; loss function.
  DOI: 10.1504/IJWBC.2022.10047487
   
  

Special Issue on: Decentralisation and New Technologies for Social Media

• A personalized recommendation method of online educational resources on social media platform  
  by Ziqian Xu 
  Abstract: Aiming at the problems of low recommendation accuracy and low user preference in traditional methods, a personalised recommendation method of online educational resources on social media platform is proposed. Firstly, the crawler technology is used to obtain the online educational resources data, and the resource data features are extracted; Then, the similarity of data features is calculated through cosine similarity, and the feature data with high similarity is fused to complete the feature preprocessing of educational resources data; Finally, the user’s demand for resource data and preference degree are determined through the user interest model, so as to construct the online educational resources personalised recommendation model, and take the educational resources data and user preference degree as the input data to complete the educational resources personalised recommendation. The experimental results show that the proposed method has high accuracy and user preference.
  Keywords: social media platform; online educational resources; personalised recommendation; reptile technology; interest model.
  DOI: 10.1504/IJWBC.2023.10047482