Seeing and Believing: Evaluating the Trustworthiness of Twitter Users

Abstract

Social networking and micro-blogging services, such as Twitter, play an important role in sharing digital information. Despite the popularity and usefulness of social media, there have been many instances where corrupted users found ways to abuse it, as for instance, through raising or lowering user's credibility. As a result, while social media facilitates an unprecedented ease of access to information, it also introduces a new challenge -that of ascertaining the credibility of shared information. Currently, there is no automated way of determining which news or users are credible and which are not. Hence, establishing a system that can measure the social media user's credibility has become an issue of great importance. Assigning a credibility score to a user has piqued the interest of not only the research community but also most of the big players on both sides -such as Facebook, on the side of industry, and political parties on the societal one. In this work, we created a model which, we hope, will ultimately facilitate and support the increase of trust in the social network communities. Our model collected data and analysed the behaviour of 50,000 politicians on Twitter. Influence score, based on several chosen features, was assigned to each evaluated user. Further, we classified the political Twitter users as either trusted or untrusted using random forest, multilayer perceptron, and support vector machine. An active learning model was used to classify any unlabelled ambiguous records from our dataset. Finally, to measure the performance of the proposed model, we used precision, recall, F1 score, and accuracy as the main evaluation metrics.

Transformative User Credibility Assessment on Twitter: A RNN based Heuristic Approach

“…Khan et. al (9) Random Forest, MLP social profiles, tweets credibility, sentiment score, and h-indexing score Real time tweets 90 8. Ahmad et.…”

Detecting User Credibility on Twitter using a Hybrid Machine Learning Model of Features’ Selection and Weighting

“…A plethora of techniques has been employed for UCD on OSNs, with many studies utilizing machine learning methods such as Support Vector Machines (SVMs) [47] [14] [48] [49] [50] [51] [52], Naïve Bayes (NB) [50], Random Forest (RF) [16] [19] [53] [54] [55] [56], XGBoost [2] [57] [58] [59], Logistic Regression (LR), [58] [60] [61]and Decision Trees (DT) [13] [14] [62] [63], or they adopt an ensemble model [56] [63]. Moreover, a hybrid approach combining SML with other techniques has been widely proposed.…”

“…This approach incorporates sentiment scores from user historical data and employs a reputation-based method for individual user profiles. While [56] delves into reputation features through a probabilistic reputation feature model, showing enhanced performance compared to raw reputation features, particularly in overall accuracy for detecting users' trust in OSNs. Additionally, [58] introduces domain-based analysis of user content by combining semantic and sentiment analyses to estimate and predict user domain-based credibility in social big data.…”

“…The author in [80] observed that users rely on easily identifiable information, such as usernames and profile pictures, to form their perceptions of credibility. Other research calculated users' credibility scores [56] based on users' social profiles, content credibility, number of retweets and likes, and the sentiment scores. Their assertion was that a higher user credibility score was indicative of increased influence and trustworthiness.…”

The Impact of the Weighted Features on the Accuracy of X-Platform’s User Credibility Detection Using Supervised Machine Learning

“…Another study [39] aimed to calculate users' credibility scores based on factors like users' social profiles, tweet credibility, the number of likes and retweets, and sentiment scores. They suggested that a higher user credibility score signifies greater influence and credibility.…”