A spatial-temporal topic model with sparse prior and RNN prior for bursty topic discovering in social networks

2021 ◽  
pp. 1-14
Author(s):  
Xiaowei Zhu ◽  
Yu Han ◽  
Shichong Li ◽  
Xinyin Wang
Keyword(s):  
Social Network ◽  
Topic Model ◽  
Data Sets ◽  
Sina Weibo ◽  
Spike And Slab Prior ◽  
The Social ◽  
Network Bursts ◽  
Sparse Prior ◽  
Binary Switching ◽  
Relationship Of

With the rapid growth of social network users, the social network has accumulated massive social network topics. However, due to the randomness of content, it becomes sparse and noisy, accompanied by many daily chats and meaningless topics, which brings challenges to bursty topics discovery. To deal with these problems, this paper proposes the spatial-temporal topic model with sparse prior and recurrent neural networks (RNN) prior for bursty topic discovering (ST-SRTM). The semantic relationship of words is learned through RNN to alleviate the sparsity. The spatial-temporal areas information is introduced to focus on bursty topics for further weakening the semantic sparsity of social network context. Besides, we introduced the “Spike and Slab” prior to decouple the sparseness and smoothness. Simultaneously, we realized the automatic discovery of social network bursts by introducing the burstiness of words as the prior and binary switching variables. We constructed multiple sets of comparative experiments to verify the performance of ST-SRTM by leveraging different evaluation indicators on real Sina Weibo data sets. The experimental results confirm the superiority of our ST-SRTM.

scholarly journals Research on Sentiment Tendency and Evolution of Public Opinions in Social Networks of Smart City

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-13 ◽  
Author(s):  
Yanni Liu ◽  
Dongsheng Liu ◽  
Yuwei Chen
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Sentiment Analysis ◽  
Smart City ◽  
Topic Model ◽  
Rapid Development ◽  
Mobile Internet ◽  
Time Curve ◽  
Public Opinions ◽  
The Social

With the rapid development of mobile Internet, the social network has become an important platform for users to receive, release, and disseminate information. In order to get more valuable information and implement effective supervision on public opinions, it is necessary to study the public opinions, sentiment tendency, and the evolution of the hot events in social networks of a smart city. In view of social networks’ characteristics such as short text, rich topics, diverse sentiments, and timeliness, this paper conducts text modeling with words co-occurrence based on the topic model. Besides, the sentiment computing and the time factor are incorporated to construct the dynamic topic-sentiment mixture model (TSTS). Then, four hot events were randomly selected from the microblog as datasets to evaluate the TSTS model in terms of topic feature extraction, sentiment analysis, and time change. The results show that the TSTS model is better than the traditional models in topic extraction and sentiment analysis. Meanwhile, by fitting the time curve of hot events, the change rules of comments in the social network is obtained.

Toward Social-Semantic Recommender Systems

2016 ◽  
Vol 7 (1) ◽  
pp. 1-30 ◽  
Author(s):  
Dalia Sulieman ◽  
Maria Malek ◽  
Hubert Kadima ◽  
Dominique Laurent
Keyword(s):  
Social Network ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Semantic Information ◽  
Basic Problem ◽  
Real Data ◽  
Data Sets ◽  
The Social ◽  
Recommendation Algorithms ◽  
Hybrid Recommendation

In this article, the authors consider the basic problem of recommender systems that is identifying a set of users to whom a given item is to be recommended. In practice recommender systems are run against huge sets of users, and the problem is then to avoid scanning the whole user set in order to produce the recommendation list. To cope with problem, they consider that users are connected through a social network and that taxonomy over the items has been defined. These two kinds of information are respectively called social and semantic information. In their contribution the authors suggest combining social information with semantic information in one algorithm in order to compute recommendation lists by visiting a limited part of the social network. In their experiments, the authors use two real data sets, namely Amazon.com and MovieLens, and they compare their algorithms with the standard item-based collaborative filtering and hybrid recommendation algorithms. The results show satisfying accuracy values and a very significant improvement of performance, by exploring a small part of the graph instead of exploring the whole graph.

scholarly journals A fusion fuzzy model for detecting phony accounts in social networks

2018 ◽  
Vol 7 (4) ◽  
pp. 2738
Author(s):  
P. Srinivas Rao ◽  
Jayadev Gyani ◽  
G. Narsimha
Keyword(s):  
Social Network ◽  
Fuzzy Model ◽  
Machine Learning Techniques ◽  
Personal Attributes ◽  
Data Sets ◽  
Learning Techniques ◽  
The Social ◽  
Using Data ◽  
Removal Technique ◽  
Normal Rank

In online social network’s phony account detection is one of the major task among the ability of genuine user from forged user account. The fundamental objective of detection of phony account framework is to detect fake account and removal technique in Social network user sites. This work concentrates on detection of phony account in which it depends on normal basis framework, transformative Algorithms and fuzzy technique. Initially, the most essential attributes including personal attributes, comparability techniques and various real user review, tweets, or comments are extricated. A direct blend of these attributes demonstrates the significance of each reviews tweets comments etc. To compute closeness measure, a consolidated strategy in view of artificial honey bee state Algorithm and fuzzy technique are utilized. Second approach is proposed to alter the best weights of the normal user attributes utilizing the social network activities/transaction and inherited Algorithm. Finally, a normal rank rationale framework is utilized to calculate the final scoring of normal user activities. The decision making of proposed approach to find phony account are variation with existing techniques user behavioral analysis using data sets and machine learning techniques such as crowdflower_sample and genuine_accounts_sample dataset of facebook and Twitter. The outcomes demonstrate that proposed strategy overcomes the previously mentioned strategies. 

scholarly journals #EsteVirusloParamosUnidos: War-like political communication on Twitter. Creating homogeneous communities in the Covid-19 crisis

2021 ◽  
Vol 27 (4) ◽  
pp. 1227-1241
Author(s):  
Anna Tous-Rovirosa ◽  
Daria Dergacheva
Keyword(s):  
Political Communication ◽  
Text Analysis ◽  
Armed Forces ◽  
Opinion Leaders ◽  
Data Sets ◽  
The Social ◽  
The Press ◽  
Computer Based ◽  
The Government ◽  
Relationship Of

This article analyses the political communication on Twitter of the Government of Spain at the height of the Covid-19 pandemic. The #estevirusloparamosunidos campaign on Twitter is monitored during the dates with the worst results in terms of fatalities (March 31th- April, 4th, 2020). The sample included in total 398 523 tweets in four data sets. Through the Social Network Analysis, the main actors and the main interactions between users are identified. The research shows a high coincidence between the typology of the Press Conference Spokespersons and the main actors on the analyzed hashtag, prioritizing the Spanish Administration and the Armed Forces. There was also a high relationship of the main opinion leaders with their “natural spectrum”. We conclude that in this hashtag there was a “war-like” atmosphere. Via the computer-based text analysis we identify that the word ‘government’ was mentioned more than medical words and that there are present some military-like terms.

scholarly journals Predicting Facebook Group Relationship

2019 ◽  
Vol 8 (11) ◽  
pp. 1862-1869 ◽  
Keyword(s):  
Social Network ◽  
Social Networking Site ◽  
Weighted Averaging ◽  
Social Actors ◽  
The Social ◽  
Sample Data ◽  
Ordered Weighted Averaging Operator ◽  
Relationship Of ◽  
Hierarchy Process ◽  
Closely Linked Group

Facebook has become the leading social networking site in most countries worldwide. It provides a diverse platform that caters to social, educational and entertainment needs of a user. So, this paper has focused on the Sociocentric Analysis of Facebook. It predicts group relationship of the Facebook social network. The paper proposes to aggregate user’s relationships with similar interests and perspectives on the basis of the way in which they provide a reaction to a post on Facebook. The paper has selected the widely used reactions on Facebook posts. The selected reactions on posts are Like, Laugh, Sad, and Wow. In this, a fuzzy pairwise relation between two users in the social network is obtained. For every pair of social actors or users, we have extracted the total number of Facebook posts to which they have reacted in a particular way over a fortnight. The number for each reaction is multiplied with the corresponding weight of the reaction computed by Analytics Hierarchy Process. This fuzzy pairwise relationship is further employed for finding the closely linked group between users by using Ordered Weighted Averaging operator. The devised algorithm has been applied to a sample data of students connected via Facebook social network. The paper has also given several application areas for the proposed work.

scholarly journals A Sparse Topic Model for Bursty Topic Discovery in Social Networks

2020 ◽  
Vol 17 (5) ◽  
pp. 816-824
Author(s):  
Lei Shi ◽  
Junping Du ◽  
Feifei Kou
Keyword(s):  
Topic Model ◽  
State Of The Art ◽  
Sina Weibo ◽  
Short Text ◽  
Qualitative And Quantitative ◽  
Topic Discovery ◽  
Spike And Slab Prior ◽  
Automatic Discovery ◽  
The Common ◽  
Sparse Topic Model

Bursty topic discovery aims to automatically identify bursty events and continuously keep track of known events. The existing methods focus on the topic model. However, the sparsity of short text brings the challenge to the traditional topic models because the words are too few to learn from the original corpus. To tackle this problem, we propose a Sparse Topic Model (STM) for bursty topic discovery. First, we distinguish the modeling between the bursty topic and the common topic to detect the change of the words in time and discover the bursty words. Second, we introduce “Spike and Slab” prior to decouple the sparsity and smoothness of a distribution. The bursty words are leveraged to achieve automatic discovery of the bursty topics. Finally, to evaluate the effectiveness of our proposed algorithm, we collect Sina weibo dataset to conduct various experiments. Both qualitative and quantitative evaluations demonstrate that the proposed STM algorithm outperforms favorably against several state-of-the-art methods

scholarly journals An Analysis of the Themes of Refuting Rumors on China's Sina Weibo During the Period of Covid-19

2021 ◽  
Vol 2 (2) ◽  
pp. 174-179
Author(s):  
Difan Guo
Keyword(s):  
Social Media ◽  
Topic Model ◽  
Release Channel ◽  
Sina Weibo ◽  
News Release ◽  
System Disease ◽  
Study Find ◽  
The Social ◽  
Media Platform ◽  
The Government

From the end of 2019 to 2020, there were countless rumors on the Internet related to COVID-19 during the viral epidemic. This study analyzed how government Weibo, the official news release channel of government social media, refuted rumors on China's leading social media platform Sina Weibo during the COVID-19 pandemic outbreak in China. This study used the LDA topic model to model the Weibo text topic and obtain the topics of the rumors that the government Weibo defied. This study find that the five main topics of rumors presented in the anti-rumor Weibo are highly related to the operation of the social system, disease prevention and treatment, and social security.  

scholarly journals An efficient method to detect communities in social networks

2021 ◽  
Author(s):  
MEHJABIN KHATOON ◽  
W AISHA BANU
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Interactions ◽  
Community Detection ◽  
Average Degree ◽  
Data Sets ◽  
Time Data ◽  
Network Graph ◽  
The Social ◽  
Metric Functions

Abstract Social networks represent the social structure, which is composed of individuals having social interactions among them. The interactions between the units in a social network represent the relations of the various social contacts and aim at finding different individuals in that network, with similar interests. It is a challenging problem to detect the social interactions between individuals with comparable considerations and desires from a large social network, which can be termed as community detection. Detection of the communities from social networks has been done by other authors previously, and many community identification algorithms were also proposed, but those communities' identification has been achieved on the online available data sets. The proposed algorithm in this paper has been named as Average Degree Newman Girvan (ADNG) algorithm, which can easily identify the communities from the real-time data sets, collected from the social network websites. The approach presented here is based on first determining the average degree of the network graph and then identifying the communities using the Newman Girvan algorithm. The proposed algorithm has been compared with four community detection algorithms, i.e., Leading eigenvector (LEC) algorithm, Fastgreedy (FG) algorithm, Leiden algorithm and Kernighan-Lin (KL) algorithm based on a few metric functions. This algorithm helps to detect communities for different domains, like for any proposed government policy, online shopping products, newly launched products in a market, etc.

Impact of empathy, perceived social impact, social worth and social network on the social entrepreneurial intention in socio-economic projects

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sumaiya Usman ◽  
Fazeelat Masood ◽  
Mubashir Ali Khan ◽  
Naveed ur Rehman Khan
Keyword(s):  
Social Network ◽  
Social Impact ◽  
Partial Least Square ◽  
Entrepreneurial Intentions ◽  
Equation Modeling ◽  
Content Type ◽  
The Social ◽  
Social Worth ◽  
Relationship Of ◽  
The Relationship

Purpose This paper aims to address essential questions regarding social entrepreneurial intentions. Do traits such as perceived social impact, social worth and social network influence, social entrepreneurial intentions among the young populous generation of Pakistan? To get a deeper insight, this paper further raises questions regarding the relationship of these predictors and social entrepreneurial intentions with empathy which is considered as a key determinant and a distinguishing trait to become a social entrepreneur. Design/methodology/approach This paper involves a quantitative research design using a partial least square structural equation modeling approach to measure the effects of the structural model. For this, a cross-sectional survey was conducted with a purposive sample of 247 university students from Pakistan. Findings Results showed a positive relationship between antecedents and social entrepreneurial intentions. Overall analysis exhibited social worth as a dominant trait and social network as the least influencing trait to impact social entrepreneurial intentions. Practical implications It will help micro and macro-level policymakers including government officials and NGOs and educators to create awareness and provide support and encouragement to individuals who aim to initiate social enterprise. Originality/value The present study makes significant contributions to the social entrepreneurship literature, as it is one of the first academic studies on social entrepreneurial intentions in Pakistan. This paper enriches the theoretical foundation by assessing the influence of perceived social impact, social worth and social network on social entrepreneurial intentions. Also, the relationship of Empathy with each of these antecedents is examined for the first time in the social entrepreneurial intentions context which is a valuable contribution both theoretically and practically.

Sign in / Sign up

Export Citation Format

Share Document