Supervised Machine Learning Applied to Link Prediction in Bipartite Social Networks

2010 ◽  
Author(s):  
Nesserine Benchettara ◽  
Rushed Kanawati ◽  
Céline Rouveirol
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Link Prediction ◽  
Supervised Machine Learning

scholarly journals Hidden Link Prediction in Criminal Networks Using the Deep Reinforcement Learning Technique

Computers ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 8 ◽  
Author(s):  
Marcus Lim ◽  
Azween Abdullah ◽  
NZ Jhanjhi ◽  
Mahadevan Supramaniam
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Network Analysis ◽  
Prediction Model ◽  
Supervised Learning ◽  
Link Prediction ◽  
Supervised Machine Learning ◽  
Criminal Networks ◽  
Criminal Network ◽  
Learning Technique

Criminal network activities, which are usually secret and stealthy, present certain difficulties in conducting criminal network analysis (CNA) because of the lack of complete datasets. The collection of criminal activities data in these networks tends to be incomplete and inconsistent, which is reflected structurally in the criminal network in the form of missing nodes (actors) and links (relationships). Criminal networks are commonly analyzed using social network analysis (SNA) models. Most machine learning techniques that rely on the metrics of SNA models in the development of hidden or missing link prediction models utilize supervised learning. However, supervised learning usually requires the availability of a large dataset to train the link prediction model in order to achieve an optimum performance level. Therefore, this research is conducted to explore the application of deep reinforcement learning (DRL) in developing a criminal network hidden links prediction model from the reconstruction of a corrupted criminal network dataset. The experiment conducted on the model indicates that the dataset generated by the DRL model through self-play or self-simulation can be used to train the link prediction model. The DRL link prediction model exhibits a better performance than a conventional supervised machine learning technique, such as the gradient boosting machine (GBM) trained with a relatively smaller domain dataset.

Rumor Detection on Twitter Using a Supervised Machine Learning Framework

2021 ◽  
pp. 452-465
Author(s):  
Hardeo Kumar Thakur ◽  
Anand Gupta ◽  
Ayushi Bhardwaj ◽  
Devanshi Verma
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Supervised Machine Learning ◽  
Learning Framework ◽  
Online Social Media ◽  
Rumor Propagation ◽  
Multiple Classification ◽  
The Government ◽  
Rumor Detection

This article describes how a rumor can be defined as a circulating unverified story or a doubtful truth. Rumor initiators seek social networks vulnerable to illimitable spread, therefore, online social media becomes their stage. Hence, this misinformation imposes colossal damage to individuals, organizations, and the government, etc. Existing work, analyzing temporal and linguistic characteristics of rumors seems to give ample time for rumor propagation. Meanwhile, with the huge outburst of data on social media, studying these characteristics for each tweet becomes spatially complex. Therefore, in this article, a two-fold supervised machine-learning framework is proposed that detects rumors by filtering and then analyzing their linguistic properties. This method attempts to automate filtering by training multiple classification algorithms with accuracy higher than 81.079%. Finally, using textual characteristics on the filtered data, rumors are detected. The effectiveness of the proposed framework is shown through extensive experiments on over 10,000 tweets.

A meta-heuristic framework based on clustering and preprocessed datasets for solving the link prediction problem

2018 ◽  
Vol 45 (6) ◽  
pp. 794-817 ◽  
Author(s):  
Reham Shawqi Barham ◽  
Ahmad Sharieh ◽  
Azzam Sleit
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Social Networks ◽  
Feature Extraction ◽  
Feature Selection ◽  
Heuristic Algorithm ◽  
Time Complexity ◽  
Link Prediction ◽  
Prediction Problem ◽  
Under Sampling

This study presents a solution to a problem commonly known as link prediction problem. Link prediction problem interests in predicting the possibility of appearing a connection between two nodes of a network, while there is no connection between these nodes in the present state of the network. Finding a solution to link prediction problem attracts variety of computer science fields such as data mining and machine learning. This attraction is due to its importance for many applications such as social networks, bioinformatics and co-authorship networks. Towards solving this problem, Evolutionary Link Prediction (EVO-LP) framework is proposed, presented, analysed and tested. EVO-LP is a framework that includes dataset preprocessing approach and a meta-heuristic algorithm based on clustering for prediction. EVO-LP is divided into preprocessing stage and link prediction stage. Feature extraction, data under-sampling and feature selection are utilised in the preprocessing stage, while in the prediction stage, a meta-heuristic algorithm based on clustering is used as an optimiser. Experimental results on a number of real networks show that EVO-LP improves the prediction quality with low time complexity.

Approaches and Applications for Sentiment Analysis

2022 ◽  
pp. 1-23
Author(s):  
M. Govindarajan
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Networking ◽  
Sentiment Analysis ◽  
Supervised Machine Learning ◽  
The Internet ◽  
Digital Form ◽  
Clear Cut ◽  
Consumer Review ◽  
Networks Analysis

With the increasing penetration of the internet, an ever-growing number of people are voicing their opinions in the numerous blogs, tweets, forums, social networking, and consumer review websites. Each such opinion has a sentiment (positive, negative, or neutral) associated with it. But the problem is that the amount of data is simply overwhelming. Methods like supervised machine learning and lexical-based approaches are available for measuring sentiments that have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis has been used in several applications including analysis of the repercussions of events in social networks, analysis of opinions about products and services. This chapter presents sentiment analysis applications and challenges with their approaches and tools. The techniques and applications discussed in this chapter will provide a clear-cut idea to the sentiment analysis researchers to carry out their work in this field.

scholarly journals Link Prediction Algorithms for Social Networks Based on Machine Learning and HARP

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 122722-122729 ◽  
Author(s):  
Hao Shao ◽  
Lunwen Wang ◽  
Yufan Ji
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Link Prediction ◽  
Prediction Algorithms

scholarly journals Missing Link Prediction Using Non-Overlapped Features and Multiple Sources of Social Networks

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 214
Author(s):  
Pokpong Songmuang ◽  
Chainarong Sirisup ◽  
Aroonwan Suebsriwichai
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Link Prediction ◽  
Classification Model ◽  
Density Level ◽  
Missing Link ◽  
Common Features ◽  
The Common

The current methods for missing link prediction in social networks focus on using data from overlapping users from two social network sources to recommend links between unconnected users. To improve prediction of the missing link, this paper presents the use of information from non-overlapping users as additional features in training a prediction model using a machine-learning approach. The proposed features are designed to use together with the common features as extra features to help in tuning up for a better classification model. The social network data sources used in this paper are Twitter and Facebook where Twitter is a main data for prediction and Facebook is a supporting data. For evaluations, a comparison using different machine-learning techniques, feature settings, and different network-density level of data source is studied. The experimental results can be concluded that the prediction model using a combination of the proposed features and the common features with Random Forest technique gained the best efficiency using percentage amount of recovering missing links and F1 score. The model of combined features yields higher percentage of recovering link by an average of 23.25% and the F1-measure by an average of 19.80% than the baseline of multi-social network source.

Sign in / Sign up

Export Citation Format

Share Document