Chalk and Cheese in Twitter: Discriminating Personal and Organization Accounts

Oentaryo, Richard J.; Low, Jia-Wei; Lim, Ee-Peng

doi:10.1007/978-3-319-16354-3_51

Cited by 11 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bots are automated accounts, which have been used for both malevolent activities like spamming and spreading false information, and also for benevolent activities like news and emergency communication (Gilani et al, 2017). Organizational accounts are social media accounts that represent an institution, corporation, agencies, news media, or a common interest group (Oentaryo et al, 2015). However, the Twitter API does not have a built-in function to distinguish these different types of accounts, which is a limitation of the current study.…”

Section: Methodsmentioning

confidence: 99%

Follow Me Too: Determinants of Transitive Tie Formation on Twitter

Malik

Lee

2020

Social Media + Society

View full text Add to dashboard Cite

Transitivity, defined as the tendency for node A to be connected to node B given that A is connected to node X and X is connected to B, has been found to be a strong predictor of tie formation in various types of social networks. As transitive ties can influence information sharing, diffusion, and attitudes toward messages, understanding the motivations and mechanisms behind transitive tie formation in online social networks (OSNs) is important. Using a large longitudinal dataset from a popular OSN, Twitter, we examine the factors affecting transitivity. Results show that the strength of ties, activity like the number of tweets, and most importantly, the number of common connections are key factors affecting transitive tie formation. Theoretical implications regarding the evolution of network structure and polarization of views as well as practical suggestions for organizations aiming to accumulate followers for information sharing are discussed.

show abstract

Section: Methodsmentioning

confidence: 99%

Follow Me Too: Determinants of Transitive Tie Formation on Twitter

Malik

Lee

2020

Social Media + Society

View full text Add to dashboard Cite

show abstract

“…This line of approaches exploits textual content such as social posts or profile descriptions of users for feature engineering or learning latent representations via deep learning approaches [5,20,21]. For example, Oentaryo et al used content, social, and temporal features and investigated several machine learning approaches such as random forests and gradient boosting [6], and showed that the gradient boosting classifier provides the best performance [13]. Wood-Doughty et al proposed using a character-based Convolutional Neural Network (CNN) [9] to learn the representation of a user's name and incorporated profile features such as the ratio of followers to friends together for classifying individual accounts [20].…”

Section: Related Workmentioning

confidence: 99%

“…As some of the features such as the number of followers or friends can have different scales compared to other features which can make the training of our model difficult, we first scaled those features using a logarithmic transformation, i.e., v 𝑘 ′ = log 10 (v 𝑘 ). Here, v 𝑘 ∈ R 13 denotes the initial values of those features. v 𝑘 ′ is then used as an input to a dense layer to output v 𝑓 ∈ R 128 as shown below using Equation 4.…”

Section: Liic Architecturementioning

confidence: 99%

A Simple Language Independent Approach for Distinguishing Individuals on Social Media

Piao

2021

Proceedings of the 32st ACM Conference on Hypertext and Social Media

View full text Add to dashboard Cite

Nowadays, the large-scale human activity traces on social media platforms such as Twitter provide new opportunities for various research areas such as mining user interests, understanding user behaviors, or conducting social science studies in a large scale. However, social media platforms contain not only individual accounts but also other accounts that are associated with non-individuals such as organizations or brands. Therefore, distinguishing individuals out of all accounts is crucial when we conduct research such as understanding human behavior based on data retrieved from those platforms. In this paper, we propose a language-independent approach for distinguishing individuals from non-individuals with the focus on leveraging their profile images, which has not been explored in previous studies. Extensive experiments on two datasets show that our proposed approach can provide competitive performance with state-of-the-art language-dependent methods, and outperforms alternative language-independent ones. CCS CONCEPTS• Human-centered computing → Social media; Social networking sites; • Computing methodologies → Supervised learning by classification.

show abstract

“…The main purpose of this analysis is to infer a latent attribute of such user. Several works have been done on a single and specific perspective such as organization detection [1,3,4,5], bot detection [2,6,7,8,9], political orientation [10], age prediction [11] etc. Twitter user classification approaches involve three major types, mainly statistical-based approaches, content-based approaches and hybrid-based approaches.…”

Section: Related Workmentioning

confidence: 99%

Organization, Bot, or Human: Towards an Efficient Twitter User Classification

Daouadi¹,

Rebaï²,

Amous³

2019

CyS

View full text Add to dashboard Cite

Today, through Twitter, researchers propose approaches for classifying user accounts. However, they have to face confidence challenges owing to the diversity of the types of data propagated throughout Twitter. In addition, the messages from Twitter are imprecise, very short and even written in many dialects and languages. Moreover, the majority of the related works focus on the overall user's activity, which makes them not suitable at the post-level classification. This paper presents an alternative approach for classifying user accounts as being accounts of bots, humans or organizations. The suggested approach consists in accurately classifying user accounts from one single post by leveraging a minimal number of language-independent features. We performed several experiments over a Twitter datasets and supervised learn-based algorithms. Our results demonstrated that simply using a minimal number of language-independent features extracted from one single post is sufficient to classify user accounts accurately and quickly. Our proposed approach yielded high F1-measure (>95%) and high AUC (>99%) using Random Forest.Keywords. Social network analysis, twitter user classification, human vs. bot vs. organization, statisticalbased approach, content-based approach, hybrid-based approach.Human 0,939 0,940 0,939 0.993 Bot 0,986 0,977 0,981 0.995 Organization 0,888 0,919 0,902 0.992

show abstract

Chalk and Cheese in Twitter: Discriminating Personal and Organization Accounts

Cited by 11 publications

References 12 publications

Follow Me Too: Determinants of Transitive Tie Formation on Twitter

Follow Me Too: Determinants of Transitive Tie Formation on Twitter

A Simple Language Independent Approach for Distinguishing Individuals on Social Media

Organization, Bot, or Human: Towards an Efficient Twitter User Classification

Contact Info

Product

Resources

About