Most recent issue published online in the International Journal of Web Based Communities.
International Journal of Web Based Communities
http://www.inderscience.com/browse/index.php?journalID=50&year=2024&vol=20&issue=1/2
Inderscience Publishers Ltd
en-uk
support@inderscience.com
International Journal of Web Based Communities
1477-8394
1741-8216
© 2024 Inderscience Enterprises Ltd.
© 2024 Inderscience Publishers Ltd
editor@inderscience.com
International Journal of Web Based Communities
https://www.inderscience.com/images/files/coverImgs/ijwbc_scoverijwbc.jpg
http://www.inderscience.com/browse/index.php?journalID=50&year=2024&vol=20&issue=1/2
-
Study on mining repeated purchase behaviour intention of online consumers based on big data clustering
http://www.inderscience.com/link.php?id=136659
In order to improve the performance of traditional repeat purchase behaviour intention mining methods in mining accuracy, a repeat purchase behaviour intention mining method of online consumer users based on big data clustering is proposed. Users' repeated purchase behaviour can be combined to reduce the dimension of network data. Extract the characteristics of repeated purchase behaviour of online consumers, judge the similarity of repeated purchase behaviour intention data of online consumers, establish a behaviour association rule mining model, and obtain the mining results of repeated purchase behaviour intention of online consumers. The simulation results show that the proposed method has high accuracy and short time to mine the repeated purchase behaviour intention of online consumers. The highest intention mining accuracy of this method can reach 99.99%.
Study on mining repeated purchase behaviour intention of online consumers based on big data clustering
Kai Niu
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 2 - 14
In order to improve the performance of traditional repeat purchase behaviour intention mining methods in mining accuracy, a repeat purchase behaviour intention mining method of online consumer users based on big data clustering is proposed. Users' repeated purchase behaviour can be combined to reduce the dimension of network data. Extract the characteristics of repeated purchase behaviour of online consumers, judge the similarity of repeated purchase behaviour intention data of online consumers, establish a behaviour association rule mining model, and obtain the mining results of repeated purchase behaviour intention of online consumers. The simulation results show that the proposed method has high accuracy and short time to mine the repeated purchase behaviour intention of online consumers. The highest intention mining accuracy of this method can reach 99.99%.]]>
10.1504/IJWBC.2024.136659
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 2 - 14
Kai Niu
School of Digital Commerce, Beijing Information Technology College, Beijing, 100018, China
big data clustering
network consumer
repeat purchase
behavioural intention
association rules
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
2
14
2024-02-15T23:20:50-05:00
-
A feature extraction method of network social media data based on fuzzy mathematical model
http://www.inderscience.com/link.php?id=136671
Aiming at the problems of low extraction accuracy and efficiency of traditional network social media data feature extraction methods, this paper proposes a network social media data feature extraction method based on fuzzy mathematical model. Firstly, by constructing the distributed data topology model and integrating the adaptive distributed data reorganisation algorithm, the network social media data is collected. Then, the continuous attributes of network social media data are discretised by using data mining algorithm, and the correlation characteristics of network social media data are analysed. Finally, the fuzzy mathematical model is used to identify the correlation characteristics of online social media data, and the feature error is corrected by the correction function to complete the feature extraction of online social media data. The experimental results show that the accuracy of feature extraction of online social media data extracted by the proposed method is as high as 98.5%.
A feature extraction method of network social media data based on fuzzy mathematical model
Zong-biao Zhang
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 15 - 26
Aiming at the problems of low extraction accuracy and efficiency of traditional network social media data feature extraction methods, this paper proposes a network social media data feature extraction method based on fuzzy mathematical model. Firstly, by constructing the distributed data topology model and integrating the adaptive distributed data reorganisation algorithm, the network social media data is collected. Then, the continuous attributes of network social media data are discretised by using data mining algorithm, and the correlation characteristics of network social media data are analysed. Finally, the fuzzy mathematical model is used to identify the correlation characteristics of online social media data, and the feature error is corrected by the correction function to complete the feature extraction of online social media data. The experimental results show that the accuracy of feature extraction of online social media data extracted by the proposed method is as high as 98.5%.]]>
10.1504/IJWBC.2024.136671
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 15 - 26
Zong-biao Zhang
Department of Education, Bo'zhou University, Bo'zhou, 236800, China
fuzzy mathematical model
fuzzy set
membership function
artificial ant colony algorithm
online social media
data feature extraction
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
15
26
2024-02-15T23:20:50-05:00
-
Study on news recommendation of social media platform based on improved collaborative filtering
http://www.inderscience.com/link.php?id=136675
Aiming at the problems of low recommendation accuracy and low user interest in the existing methods, a news recommendation of social media platform based on improved collaborative filtering is designed. The initial key features of news data are determined, and the occurrence frequency of key features is counted by chi square, so as to realise feature extraction. First, we calculate the mutual information between different news data features, determine the correlation degree between features, and remove the data with similar features and low correlation degree. Then, the collaborative filtering algorithm is improved by adding timing update, trust and other data in collaborative filtering. Finally, the improved collaborative filtering algorithm is used to build a recommendation model, and the news data characteristics and user preference data are input into the model to complete the recommendation. The experimental results show that the news data recommended by the proposed method has high accuracy and high user interest.
Study on news recommendation of social media platform based on improved collaborative filtering
Bin Wu
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 27 - 37
Aiming at the problems of low recommendation accuracy and low user interest in the existing methods, a news recommendation of social media platform based on improved collaborative filtering is designed. The initial key features of news data are determined, and the occurrence frequency of key features is counted by chi square, so as to realise feature extraction. First, we calculate the mutual information between different news data features, determine the correlation degree between features, and remove the data with similar features and low correlation degree. Then, the collaborative filtering algorithm is improved by adding timing update, trust and other data in collaborative filtering. Finally, the improved collaborative filtering algorithm is used to build a recommendation model, and the news data characteristics and user preference data are input into the model to complete the recommendation. The experimental results show that the news data recommended by the proposed method has high accuracy and high user interest.]]>
10.1504/IJWBC.2024.136675
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 27 - 37
Bin Wu
The School of Network Communication, Zhejiang Yuexiu University, Shaoxing, 312000, China
improving collaborative filtering
social media platform
news recommendation
active learning
covariance matrix
information gain
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
27
37
2024-02-15T23:20:50-05:00
-
Anomaly detection method of social media user information based on data mining
http://www.inderscience.com/link.php?id=136674
Aiming at the problems of low detection accuracy, recall and F1 value of traditional social media user information anomaly detection methods, a social media user information anomaly detection method based on data mining is proposed. Firstly, we clean the social media data and eliminate the invalid and missing values in the data. Then, we filter the abnormal user information in the social media data through the unsupervised k-means algorithm in data mining. Finally, according to the screening results, we calculate the text word segmentation of user information, obtain the similarity of word frequency, and complete the detection of abnormal user information. The method provided by social media has the highest accuracy of 97.5%, which is the highest exception detection rate of 97.5% and the highest exception detection rate of social media.
Anomaly detection method of social media user information based on data mining
Xiaoyan Wan
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 38 - 50
Aiming at the problems of low detection accuracy, recall and F1 value of traditional social media user information anomaly detection methods, a social media user information anomaly detection method based on data mining is proposed. Firstly, we clean the social media data and eliminate the invalid and missing values in the data. Then, we filter the abnormal user information in the social media data through the unsupervised k-means algorithm in data mining. Finally, according to the screening results, we calculate the text word segmentation of user information, obtain the similarity of word frequency, and complete the detection of abnormal user information. The method provided by social media has the highest accuracy of 97.5%, which is the highest exception detection rate of 97.5% and the highest exception detection rate of social media.]]>
10.1504/IJWBC.2024.136674
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 38 - 50
Xiaoyan Wan
Qingdao Vocation and Technical College of Hotel Management, Qingdao, 266100, China
data mining
social media
user information
K-means
Weibo
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
38
50
2024-02-15T23:20:50-05:00
-
A semantic retrieval model of social media data based on statistical theory
http://www.inderscience.com/link.php?id=136657
Aiming at the problems of low retrieval accuracy and efficiency in semantic retrieval model of social media data, this paper studies semantic retrieval model of social media data based on statistical theory. Statistical theory and ontology of semantic retrieval information of social media data are analysed to complete the labelling process of retrieval information. The semantic retrieval model of social media data is constructed by calculating the similarity of semantic distance and information amount and using statistical theory. Experimental results show that the recall rate of the proposed method is as high as 94%, and the accuracy is as high as 92%, both higher than other methods, and the retrieval time is only 18.2 s. Therefore, the semantic retrieval effect of social media data is good, and the semantic retrieval accuracy and efficiency of social media data are effectively improved.
A semantic retrieval model of social media data based on statistical theory
Fuwang Li
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 51 - 62
Aiming at the problems of low retrieval accuracy and efficiency in semantic retrieval model of social media data, this paper studies semantic retrieval model of social media data based on statistical theory. Statistical theory and ontology of semantic retrieval information of social media data are analysed to complete the labelling process of retrieval information. The semantic retrieval model of social media data is constructed by calculating the similarity of semantic distance and information amount and using statistical theory. Experimental results show that the recall rate of the proposed method is as high as 94%, and the accuracy is as high as 92%, both higher than other methods, and the retrieval time is only 18.2 s. Therefore, the semantic retrieval effect of social media data is good, and the semantic retrieval accuracy and efficiency of social media data are effectively improved.]]>
10.1504/IJWBC.2024.136657
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 51 - 62
Fuwang Li
Department of Mechanical and Electronic Engineering, Xinxiang Vocational and Technical College, Xinxiang, 453006, China
statistical theory
statistical language model
social media data
semantic retrieval
retrieval model
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
51
62
2024-02-15T23:20:50-05:00
-
Research and judgement method of social network hot news public opinion based on knowledge graph
http://www.inderscience.com/link.php?id=136673
In order to improve the accuracy of the judgement of the development of news public opinion, this paper puts forward the research and judgement method of social network hot news public opinion based on knowledge graph. Through corpus annotation, character coding and time slice processing, the corpus of hot news on the internet is pre-processed, and the processed corpus information is used to construct knowledge atlas. In order to improve the accuracy of the analysis of news elements, the map is composed of several sub-maps with the most closely connected relationship. Finally, in combination with the real-time nature of news, the development of news public opinion is judged from the three perspectives of news evolution, spread and news heat. The test results show that the error of the method is less than 2% for the judgement of public opinion evolution degree, spread breadth and news heat.
Research and judgement method of social network hot news public opinion based on knowledge graph
Gelang Li
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 63 - 74
In order to improve the accuracy of the judgement of the development of news public opinion, this paper puts forward the research and judgement method of social network hot news public opinion based on knowledge graph. Through corpus annotation, character coding and time slice processing, the corpus of hot news on the internet is pre-processed, and the processed corpus information is used to construct knowledge atlas. In order to improve the accuracy of the analysis of news elements, the map is composed of several sub-maps with the most closely connected relationship. Finally, in combination with the real-time nature of news, the development of news public opinion is judged from the three perspectives of news evolution, spread and news heat. The test results show that the error of the method is less than 2% for the judgement of public opinion evolution degree, spread breadth and news heat.]]>
10.1504/IJWBC.2024.136673
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 63 - 74
Gelang Li
Fuyang Normal University, Fuyang 236000, China
knowledge graph
hot news on social networks
public opinion research and judgement
corpus processing
connectivity relation
real time
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
63
74
2024-02-15T23:20:50-05:00
-
Data mining method of mobile e-commerce consumer purchase behaviour
http://www.inderscience.com/link.php?id=136650
In order to improve the accuracy and efficiency of data mining of consumer purchase behaviour in mobile e-commerce, a data mining method of consumer purchase behaviour in mobile e-commerce is proposed. Firstly, through the calculation of support in principal component analysis, the data characteristics of mobile e-commerce consumers' purchase behaviour are extracted. Then, the original residual of purchase behaviour data is calculated through iterative test, and the original feature data is corrected to complete the preprocessing. Finally, the Boolean rules in association rules are used to determine the association degree between purchase behaviour data, and the minimum threshold of purchase behaviour data is calculated. By establishing the correlation function of mobile e-commerce consumer purchase behaviour data, mining the characteristic information of mobile e-commerce consumer purchase behaviour data, and completing the purchase behaviour data mining. The results show that the highest accuracy of data mining is 98.1%.
Data mining method of mobile e-commerce consumer purchase behaviour
Shuang Li
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 75 - 87
In order to improve the accuracy and efficiency of data mining of consumer purchase behaviour in mobile e-commerce, a data mining method of consumer purchase behaviour in mobile e-commerce is proposed. Firstly, through the calculation of support in principal component analysis, the data characteristics of mobile e-commerce consumers' purchase behaviour are extracted. Then, the original residual of purchase behaviour data is calculated through iterative test, and the original feature data is corrected to complete the preprocessing. Finally, the Boolean rules in association rules are used to determine the association degree between purchase behaviour data, and the minimum threshold of purchase behaviour data is calculated. By establishing the correlation function of mobile e-commerce consumer purchase behaviour data, mining the characteristic information of mobile e-commerce consumer purchase behaviour data, and completing the purchase behaviour data mining. The results show that the highest accuracy of data mining is 98.1%.]]>
10.1504/IJWBC.2024.136650
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 75 - 87
Shuang Li
Department of Information and Mechatronics Engineering, Hunan International Economics University, Changsha 410205, China; Department of Graduate School, Lyceum of the Philippines University, Manila Campus, Manila 1002, Philippines
principal component analysis
iterative test method
Boolean rule
mobile e-commerce
consumer buying behaviour
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
75
87
2024-02-15T23:20:50-05:00
-
Cross-modal retrieval of large-scale images in social media based on spatial distribution entropy
http://www.inderscience.com/link.php?id=136649
In order to improve the cross-modal retrieval accuracy of large-scale social media images, a cross-modal retrieval method for large-scale social media images based on spatial distribution entropy is proposed. First, extract the information features of the colour and texture of the image. Then, use the image cross-modal retrieval method based on the spatial distribution entropy to calculate the spatial distribution entropy of the colour information and texture information features in the image. Finally, use the Euclidean distance to judge the space between social media images. The matching degree of the distribution entropy, according to the matching degree, is used to judge whether the image cross-modal retrieval is successful or not. The experimental results verify that the proposed method can implement comprehensive retrieval according to the specific characteristics of the retrieved images, and the matching degree of image retrieval is greater than 95%, and the retrieval accuracy is high.
Cross-modal retrieval of large-scale images in social media based on spatial distribution entropy
Jie Ding; Guotao Zhao; Fang Xu
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 88 - 101
In order to improve the cross-modal retrieval accuracy of large-scale social media images, a cross-modal retrieval method for large-scale social media images based on spatial distribution entropy is proposed. First, extract the information features of the colour and texture of the image. Then, use the image cross-modal retrieval method based on the spatial distribution entropy to calculate the spatial distribution entropy of the colour information and texture information features in the image. Finally, use the Euclidean distance to judge the space between social media images. The matching degree of the distribution entropy, according to the matching degree, is used to judge whether the image cross-modal retrieval is successful or not. The experimental results verify that the proposed method can implement comprehensive retrieval according to the specific characteristics of the retrieved images, and the matching degree of image retrieval is greater than 95%, and the retrieval accuracy is high.]]>
10.1504/IJWBC.2024.136649
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 88 - 101
Jie Ding
Guotao Zhao
Fang Xu
College of Technology, Hubei Engineering University, Xiaogan, China ' School of Foreign Languages, Hubei Engineering University, Xiaogan, China ' School of Computer and Information Science, Hubei Engineering University, Xiaogan, China
spatial distribution entropy
social media
large-scale
cross-modal
image
retrieval
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
88
101
2024-02-15T23:20:50-05:00
-
Prediction method of e-commerce consumers' purchase behaviour based on social network data mining
http://www.inderscience.com/link.php?id=136648
In order to effectively improve the prediction accuracy of e-commerce consumers' purchase behaviour and shorten the prediction time of e-commerce consumers' purchase behaviour, a prediction method of e-commerce consumers' purchase behaviour based on social network data mining is proposed. Firstly, according to the statistical characteristics of e-commerce consumers' purchase behaviour, data mining method is used to extract the characteristics of e-commerce consumers' purchase behaviour. Secondly, the social network analysis method is used to analyse the purchase behaviour characteristics of e-commerce consumers and the social network model. Finally, build the prediction model of e-commerce consumers' purchase behaviour to realise the prediction of e-commerce consumers' purchase behaviour. The experimental results show that the proposed method has a good effect on the prediction of e-commerce consumers' purchase behaviour, and can effectively improve the prediction accuracy of e-commerce consumers' purchase behaviour. The prediction deviation rate is only 1.8%.
Prediction method of e-commerce consumers' purchase behaviour based on social network data mining
Ming Yang
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 102 - 113
In order to effectively improve the prediction accuracy of e-commerce consumers' purchase behaviour and shorten the prediction time of e-commerce consumers' purchase behaviour, a prediction method of e-commerce consumers' purchase behaviour based on social network data mining is proposed. Firstly, according to the statistical characteristics of e-commerce consumers' purchase behaviour, data mining method is used to extract the characteristics of e-commerce consumers' purchase behaviour. Secondly, the social network analysis method is used to analyse the purchase behaviour characteristics of e-commerce consumers and the social network model. Finally, build the prediction model of e-commerce consumers' purchase behaviour to realise the prediction of e-commerce consumers' purchase behaviour. The experimental results show that the proposed method has a good effect on the prediction of e-commerce consumers' purchase behaviour, and can effectively improve the prediction accuracy of e-commerce consumers' purchase behaviour. The prediction deviation rate is only 1.8%.]]>
10.1504/IJWBC.2024.136648
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 102 - 113
Jie Ding
Guotao Zhao
Fang Xu
School of Business, Chongqing College of Electronic Engineering, Chongqing 401331, China
social network analysis method
data mining methods
e-commerce consumers
purchase behaviour
prediction model
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
102
113
2024-02-15T23:20:50-05:00
-
An encryption of social network user browsing trajectory data based on adversarial neural network
http://www.inderscience.com/link.php?id=136651
In order to solve the problems of high information loss rate, poor encryption effect and long encryption time existing in traditional social network user browsing trajectory data encryption methods, this paper proposes an encryption method of social network user browsing trajectory data based on adversarial neural network. Mutual information is used to extract browsing characteristics of social network users and calculate browsing path similarity of social network users, so as to determine the clustering centre of browsing trajectory data and realise browsing trajectory data mining. Combining with adversarial neural network, the symmetric encryption and decoding model is designed, and the user browsing feature data is input into the model to realise the user browsing feature data encryption. Experimental results show that the information loss rate of the proposed method is always lower than 5%, the encryption effect is good, and the average encryption time is 53 ms.
An encryption of social network user browsing trajectory data based on adversarial neural network
Xinliang Wang
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 114 - 127
In order to solve the problems of high information loss rate, poor encryption effect and long encryption time existing in traditional social network user browsing trajectory data encryption methods, this paper proposes an encryption method of social network user browsing trajectory data based on adversarial neural network. Mutual information is used to extract browsing characteristics of social network users and calculate browsing path similarity of social network users, so as to determine the clustering centre of browsing trajectory data and realise browsing trajectory data mining. Combining with adversarial neural network, the symmetric encryption and decoding model is designed, and the user browsing feature data is input into the model to realise the user browsing feature data encryption. Experimental results show that the information loss rate of the proposed method is always lower than 5%, the encryption effect is good, and the average encryption time is 53 ms.]]>
10.1504/IJWBC.2024.136651
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 114 - 127
Jie Ding
Guotao Zhao
Fang Xu
Binzhou Civil Air Defense Office, Binzhou 256600, Shandong, China; Binzhou Housing and Urban Rural Development Bureau, Binzhou 256600, Shandong, China
adversarial neural network
social network
user browsing trajectory
data encryption
data mining
symmetric encryption
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
114
127
2024-02-15T23:20:50-05:00
-
Social media user information security encryption method based on chaotic algorithm
http://www.inderscience.com/link.php?id=136672
In order to overcome the problems of small entropy, poor image definition and low information security in traditional methods, this paper proposes a social media user information security encryption method based on chaotic algorithm. Firstly, the general social media user information encryption architecture was designed by chaotic image encryption method. Secondly, logistic chaotic map was defined according to the principle of fast chaotic encryption. Then, the chaotic function of social media user information was obtained by 'scrambling diffusion' algorithm. Finally, the chaotic sequence was generated by chaotic algorithm to realise the information security encryption of social media users. The experimental results show that the attack blocking probability of this method is still more than 0.83, and the entropy of this method is 7.875, which shows that the anti attack effect of this method is remarkable.
Social media user information security encryption method based on chaotic algorithm
Xiao Yi
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 128 - 138
In order to overcome the problems of small entropy, poor image definition and low information security in traditional methods, this paper proposes a social media user information security encryption method based on chaotic algorithm. Firstly, the general social media user information encryption architecture was designed by chaotic image encryption method. Secondly, logistic chaotic map was defined according to the principle of fast chaotic encryption. Then, the chaotic function of social media user information was obtained by 'scrambling diffusion' algorithm. Finally, the chaotic sequence was generated by chaotic algorithm to realise the information security encryption of social media users. The experimental results show that the attack blocking probability of this method is still more than 0.83, and the entropy of this method is 7.875, which shows that the anti attack effect of this method is remarkable.]]>
10.1504/IJWBC.2024.136672
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 128 - 138
Jie Ding
Guotao Zhao
Fang Xu
Modern Education Technology Center, Hunan Communication Polytechnic, Changsha 410132, China
chaotic algorithm
scrambling diffusion
social media users
information security encryption
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
128
138
2024-02-15T23:20:50-05:00
-
An evolution trend evaluation of social media network public opinion based on unsupervised learning
http://www.inderscience.com/link.php?id=136653
In order to overcome the problems of poor evaluation effect, low accuracy and time-consuming of traditional methods, an evolution trend evaluation method of social media network public opinion based on unsupervised learning is proposed. Firstly, we establish the evaluation index system of public opinion evolution trend of social media network. Then, the graph convolution neural network is used to combine the evaluation index with neighbourhood features to extract the mixed features of public opinion evolution trend, and the correlation degree of mixed features is calculated by correlation ranking method. Finally, the evaluation model of public opinion evolution trend based on unsupervised learning is constructed according to the correlation degree of mixed features, and the evaluation results are obtained. The experimental results show that the proposed method has good evaluation effect of public opinion evolution trend, high evaluation accuracy and short evaluation time.
An evolution trend evaluation of social media network public opinion based on unsupervised learning
Yanhua Shen
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 139 - 152
In order to overcome the problems of poor evaluation effect, low accuracy and time-consuming of traditional methods, an evolution trend evaluation method of social media network public opinion based on unsupervised learning is proposed. Firstly, we establish the evaluation index system of public opinion evolution trend of social media network. Then, the graph convolution neural network is used to combine the evaluation index with neighbourhood features to extract the mixed features of public opinion evolution trend, and the correlation degree of mixed features is calculated by correlation ranking method. Finally, the evaluation model of public opinion evolution trend based on unsupervised learning is constructed according to the correlation degree of mixed features, and the evaluation results are obtained. The experimental results show that the proposed method has good evaluation effect of public opinion evolution trend, high evaluation accuracy and short evaluation time.]]>
10.1504/IJWBC.2024.136653
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 139 - 152
Jie Ding
Guotao Zhao
Fang Xu
School of Public Management, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, China; Nanjing Forestry University, Nanjing, Jiangsu, 210037, China
unsupervised learning
social media networks
evolution of network public opinion
evolution trend assessment
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
139
152
2024-02-15T23:20:50-05:00
-
Data mining method of social media hot topics based on time series clustering
http://www.inderscience.com/link.php?id=136647
In order to overcome the problems of large analysis error and low mining accuracy of traditional hot topic data mining methods, this paper proposes a new social media hot topic data mining method based on time series clustering. Firstly, the topic feedback forms of reading, comment, forwarding and praise are taken as the research objects. Secondly, the contribution value of various data in the topic heat is calculated to obtain the topic heat results. Finally, take the topic value as the goal and follow-up reports as the index to realise data mining. The test results show that the design method can accurately analyse the data of reading, comments, forwarding and likes. The analysis results of the number of follow-up reports have a high degree of fit with the actual results, and have a high mining accuracy, which is close to 100%.
Data mining method of social media hot topics based on time series clustering
Wei Wang
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 153 - 163
In order to overcome the problems of large analysis error and low mining accuracy of traditional hot topic data mining methods, this paper proposes a new social media hot topic data mining method based on time series clustering. Firstly, the topic feedback forms of reading, comment, forwarding and praise are taken as the research objects. Secondly, the contribution value of various data in the topic heat is calculated to obtain the topic heat results. Finally, take the topic value as the goal and follow-up reports as the index to realise data mining. The test results show that the design method can accurately analyse the data of reading, comments, forwarding and likes. The analysis results of the number of follow-up reports have a high degree of fit with the actual results, and have a high mining accuracy, which is close to 100%.]]>
10.1504/IJWBC.2024.136647
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 153 - 163
Jie Ding
Guotao Zhao
Fang Xu
College of Information Engineering, Henan Industry and Trade Vocational College, Zhengzhou, Henan 450053, China
time series clustering
social media hot topics
data mining
topic heat
topic value
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
153
163
2024-02-15T23:20:50-05:00
-
Factors affecting attachment behaviours, cognitive and emotional evaluations on Facebook live streams
http://www.inderscience.com/link.php?id=136656
The research trend of live streams has become increasingly popular in recent years. Therefore, the study aimed to investigate the factors of live streaming platforms that successfully stimulate consumers to generate corresponding behavioural responses. The stimulus-organism-response model was used as a theoretical background. With a sample of 324 online consumers, the study attempted to investigate the relationships among the constructs. The findings showed that stimuli, (e.g., live streamers' professional ability, relationship connection with consumers, and social presence of the live streaming environment) have a significant influence on the organism, (e.g., cognitive and emotional evaluation of live streamers), and thus consumers' responses (e.g., emotional and merchant attachment behaviours). Furthermore, this study found that the live broadcast platform's pre-factors and the live broadcaster's cognitive and emotional evaluations positively and significantly impact their attachment behaviour. The findings provide information to improve their live streaming platforms and businesses.
Factors affecting attachment behaviours, cognitive and emotional evaluations on Facebook live streams
Van Kien Pham
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 164 - 179
The research trend of live streams has become increasingly popular in recent years. Therefore, the study aimed to investigate the factors of live streaming platforms that successfully stimulate consumers to generate corresponding behavioural responses. The stimulus-organism-response model was used as a theoretical background. With a sample of 324 online consumers, the study attempted to investigate the relationships among the constructs. The findings showed that stimuli, (e.g., live streamers' professional ability, relationship connection with consumers, and social presence of the live streaming environment) have a significant influence on the organism, (e.g., cognitive and emotional evaluation of live streamers), and thus consumers' responses (e.g., emotional and merchant attachment behaviours). Furthermore, this study found that the live broadcast platform's pre-factors and the live broadcaster's cognitive and emotional evaluations positively and significantly impact their attachment behaviour. The findings provide information to improve their live streaming platforms and businesses.]]>
10.1504/IJWBC.2024.136656
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 164 - 179
Jie Ding
Guotao Zhao
Fang Xu
Ho Chi Minh City University of Economics and Finance (UEF), 141-145 Dien Bien Phu, Ward 15, Binh Thanh District, Ho Chi Minh City, Vietnam
live streams
Facebook
attachment behaviour
cognitive
emotional
evaluation
stimulus-organism-response
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
164
179
2024-02-15T23:20:50-05:00
-
YouTube and the production of online video cultures in Rural South India
http://www.inderscience.com/link.php?id=136669
This article examines how a group of villagers in rural South India shot to online fame by posting entertaining audio-visual content on YouTube. Motivated to showcase the countryside culture, villagers began sharing short videos depicting their daily rural lives. Some of their videos have gone viral, garnered millions of views, and amassed thousands of subscribers. Inspired by the positive reception, village video makers have taken their YouTube productions professionally and created a unique brand identity for their media content. From short films to web series, village video-makers produce a wide variety of audio-visual content. Village video creators have accumulated a massive online following, digital stardom, and social media fame. This paper maps the emerging vernacular online video-sharing cultures and the rise of rural micro-celebrities through a close reading of a specific case study, 'my village show, ' one of the popular village-based YouTube channels in South India.
YouTube and the production of online video cultures in Rural South India
Srikanth Nayaka; Vamshi Krishna Reddy Vemireddy; Prabha Shankar Dwivedi
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 180 - 197
This article examines how a group of villagers in rural South India shot to online fame by posting entertaining audio-visual content on YouTube. Motivated to showcase the countryside culture, villagers began sharing short videos depicting their daily rural lives. Some of their videos have gone viral, garnered millions of views, and amassed thousands of subscribers. Inspired by the positive reception, village video makers have taken their YouTube productions professionally and created a unique brand identity for their media content. From short films to web series, village video-makers produce a wide variety of audio-visual content. Village video creators have accumulated a massive online following, digital stardom, and social media fame. This paper maps the emerging vernacular online video-sharing cultures and the rise of rural micro-celebrities through a close reading of a specific case study, 'my village show, ' one of the popular village-based YouTube channels in South India.]]>
10.1504/IJWBC.2024.136669
International Journal of Web Based Communities, Vol. 20, No. 1/2 (2024) pp. 180 - 197
Srikanth Nayaka
Vamshi Krishna Reddy Vemireddy
Prabha Shankar Dwivedi
Indian Institute of Technology Tirupati, Yerpedu †Venkatagiri Road, Yerpedu Post, Tirupati District, Andhra Pradesh, 517619, India ' University of Hyderabad, Prof. CR Rao Road, Gachibowli, Hyderabad, Telangana, 500046, India ' Indian Institute of Technology Tirupati, Yerpedu †Venkatagiri Road, Yerpedu Post, Tirupati District, Andhra Pradesh, 517619, India
YouTube
platformisation
video cultures
vernacular creativity
digital cultures
digital labour
microcelebrity
digital India
South India
global south
2024-02-15T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
20
1/2
180
197
2024-02-15T23:20:50-05:00