Twitter Bots

description27 papers

group1 follower

lightbulbAbout this topic

Twitter bots are automated accounts on the Twitter platform that generate and post content without human intervention. They can perform various functions, including disseminating information, engaging with users, or manipulating public opinion, often utilizing algorithms to operate at scale and influence social interactions.

lightbulbAbout this topic

Key research themes

1. How can automated bots on Twitter be accurately detected and classified among benign, malicious, and influence bots?

Detecting social media bots, especially on Twitter, is essential due to their increasing prevalence and impact on information dissemination and political discourse. This theme focuses on developing and evaluating machine learning and AI-driven methodologies to identify bots, distinguishing between various bot types, and tackling the challenges of evolving bot sophistication and limited labeled data. Accurate classification aids not only platform integrity but also improves research validity in studies of online phenomena.

The DARPA Twitter Bot Challenge

by Vadim Kagan

2024, Computer

Key finding: The DARPA Twitter Bot Challenge demonstrated that a hybrid analytical approach combining machine learning with manual feature crafting and network analysis was necessary to detect influence bots focused on a specific topic... Read more

articleView Paper downloadDownload

A one-class classification approach for bot detection on Twitter

by Raul Monroy

2024, Computers & Security

Key finding: This paper proposed the use of one-class classification methods trained solely on legitimate human account data, circumventing the need for diverse bot training samples. Their experiments showed that one-class classifiers can... Read more

articleView Paper downloadDownload

TweezBot: An AI-Driven Online Media Bot Identification Algorithm for Twitter Social Networks

by Rachit Shukla

2022, Electronics

Key finding: TweezBot, an AI-driven multi-layer classification framework, was introduced, utilizing a blend of profile-centric and activity-centric features unique to Twitter for bot detection. Comparative evaluation against established... Read more

articleView Paper downloadDownload

On Profiling Bots in Social Media

by Richard Oentaryo

2021, Lecture Notes in Computer Science

Key finding: This study proposed a nuanced behavioral categorization of Twitter bots into broadcast, consumption, and spam bots, extending beyond the common malicious/non-malicious dichotomy. Their profiling framework integrates... Read more

articleView Paper downloadDownload

Automatic Detection of Bot-generated Tweets

by sow babacar

2024, Zenodo (CERN European Organization for Nuclear Research)

Key finding: The paper addressed the detection of individual bot-generated tweets using pretrained language models like RoBERTa, especially against advanced text-generation methods such as GPT-2. It was found that detecting bot-generated... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

2. What are the behavioral patterns and roles of social bots in political discourse and disinformation campaigns on Twitter?

Social bots play influential and sometimes covert roles in shaping political conversations and spreading disinformation. This theme analyzes the specific strategies bots employ, their collective behavior patterns, and their impact in propaganda, activism, protests, and election-related discourse. Understanding these behavioral signatures enables better recognition of coordinated manipulation and informs both detection methods and policy measures.

Protesting Corruption on Twitter: Is It a Bot or Is It a Person?

by Elena Karahanna

2023, Academy of Management Discoveries

Key finding: In a case study of Brazil’s Mensalão corruption protest on Twitter, central actors in the network were found to include both humans and automated bots that amplified protest information. The study revealed how bots... Read more

articleView Paper downloadDownload

Strategies and Influence of Social Bots in a 2017 German state election - A case study on Twitter

by Lennart Hofeditz

2022, ArXiv

Key finding: Analyzing social bots active in the run-up to the 2017 North Rhine-Westphalia state election, 61 social bots were identified; however, they showed no evidence of collective political strategies or significant influence. This... Read more

articleView Paper downloadDownload

Collective behaviour of social bots is encoded in their temporal Twitter activity

by Andrej Duh

2022

Key finding: Using tweet activity data from the UK EU referendum campaign, this study demonstrated that populations of bots exhibit distinct collective temporal activity characterized by weak pairwise correlations but coordinated spiking... Read more

articleView Paper downloadDownload

Algorithmic Agents in the Hybrid Media System: Social Bots, Selective Amplification, and Partisan News about COVID-19

by Zening DUAN

2023, Human Communication Research

Key finding: This study found that Twitter bots represented about 9% of accounts discursively active during early COVID-19 coverage, selectively amplifying topics aligned with partisan narratives. Bot activity preceded aligned partisan... Read more

articleView Paper downloadDownload

#bias: Measuring the Tweeting Behavior of Propagandists

by Hans Klein

2023, Proceedings of the International AAAI Conference on Web and Social Media

Key finding: Examining Twitter propagandists involved in politically charged events, the study identified behaviors distinguishing them from neutral users: high tweet volumes in short time frames, predominance of retweets over original... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

3. How do bots interact with humans and influence information ecosystems on Twitter and related platforms?

Bots on social media do not act in isolation but form complex interaction networks with humans that shape the structure and dynamics of information ecosystems. This theme investigates human-bot interaction patterns, the emergence of network motifs due to bot strategies, and how bots affect news sharing, information diffusion, and media ranking on Twitter and Telegram. Insights here are crucial for understanding hybrid media ecosystems and designing countermeasures.

Emergent local structures in an ecosystem of social bots and humans on Twitter

by Janos Kertesz

2024, EPJ Data Science

Key finding: Through an experimental deployment of six AI-driven social bots with distinct interaction strategies on Twitter, this study found that different bot targeting strategies (trend-targeting, keyword-targeting, user-targeting)... Read more

articleView Paper downloadDownload

Bots or journalists? News sharing on Twitter

by Anders Olof Larsson

2022, Communications

Key finding: Comparative analysis of link sharing to news media on Twitter in Sweden and Norway showed that automated 'bot' accounts actively participate in driving traffic to news outlets, sometimes indistinguishable from humans in... Read more

articleView Paper downloadDownload

An exploratory analysis of COVID bot vs human disinformation dissemination stemming from the Disinformation Dozen on Telegram

by Samantha Clark and

2024

Key finding: This study analyzing Telegram identified that while the 'Disinformation Dozen' initiated large volumes of COVID-19 disinformation, bots on Telegram were more active in conversations, and humans were the primary forwarders... Read more

articleView Paper downloadDownload

Telegram Channels and Bots: A Ranking of Media Outlets Based in Spain

by Carlos Castro

2023, Societies

Key finding: Examining Telegram channel usage by Spanish media outlets, the study compiled a ranking based on subscriber counts, revealing that many channels lacked verification, raising risks for fake channel proliferation. The results... Read more

articleView Paper downloadDownload

keyboard_arrow_downShow more

All papers in Twitter Bots

Bots, reality shows and Greek political parties: Tracking bots and their political propaganda in Greece

by Maria Sidiropoulou

2025, Proceedings of the Conference for Truth and Trust Online 2019

The use of twitter bots in political campaigns and influence operations has come increasingly under the academic and journalistic limelight. In this study, we present the first data-driven journalistic investigation on the presence of... more

descriptionView Paper arrow_downwardDownload

Analyzing X mentions to uncover micro-clusters interfering in political campaigns: a case study during the Spanish elections

by Francisco José García Ull

2025, Frontiers in Communication

Introduction: Coordinated influence campaigns on social networks pose a growing threat to democratic discourse, especially during electoral periods. This study investigates such efforts within political conversations during the Spanish... more

descriptionView Paper arrow_downwardDownload

Evaluating the Influence of Twitter Bots via Agent-Based Social Simulation

by Aldo Averza and

2024, Evaluating_the_Influence_of_Twitter_Bots_via_Agent_Based_Social_Simulation

Social Media is used by many as a source of information for current world events, followed by publicly sharing their sentiment about these events. However, when the shared information is not trustworthy and receives a large number of interactions, it alters the public's perception of authentic and false information, particularly when the origin of these stories comes from malicious sources. Over the past decade, there has been an influx of users on the Twitter social network, many of them automated bot accounts with the objective of participating in misinformation campaigns that heavily influence user susceptibility to fake information. This can affect public opinion on real-life matters, as previously seen in the 2020 presidential elections and the current COVID-19 epidemic, both plagued with misinformation. In this paper, we propose an agent-based social simulation environment that utilizes the social network Twitter, with the objective of evaluating how the beliefs of agents representing regular Twitter users can be influenced by malicious users scattered throughout Twitter with the sole purpose of spreading misinformation. We applied two scenarios to compare how these regular agents behave in the Twitter network, with and without malicious agents, to study how much influence malicious agents have on the general susceptibility of the regular users. To achieve this, we implemented a belief value system to measure how impressionable an agent is when encountering misinformation and how its behavior gets affected. The results indicated similar outcomes in the two scenarios as the affected belief value changed for these regular agents, exhibiting belief in the misinformation. Although the change in belief value occurred slowly, it had a profound effect when the malicious agents were present, as many more regular agents started believing in misinformation. INDEX TERMS Agent-based modeling, agent-based social simulation, multi-agent systems, social media, twitter, twitter bot.

FIGURE 1. High-level structure of multi-agent systems [23].

FIGURE 2. The high-level structure view of the proposed model.

FIGURE 3. State diagram showing how the belief value states are distributed.

Algorithm 2 Neutral Agent Pseudocode for Fake Believer State Details on how the Twitter algorithm works are unknown to the public, so we work under the assumption that all users use this feature, and the factors taken into account are the number of engaged users and topic similarity.

FIGURE 5. Distribution of agents in the network for scenario 1.

FIGURE 7. Average belief value per time step for scenario 1. FIGURE 6. (a) Number of tweets per type (b) Impressions and Engagements per type of tweet for scenario 1

FIGURE 8. Distribution of agents in the network for scenario 2.

FIGURE 10. Average belief value per time step for scenario 2.

FIGURE 9. (a) Number of tweets per type. (b) Impressions and Engagements per type of tweet for scenario 2.

to approximate our simulation as much as possible to t data extracted from Twitter. Starting with deceptive agents, we chose a 15% distribution as that was the percentage of accounts with bot behavior from our findings with t Botometer API. For news agents, we started with 5%, as tho were approximately the number of verified accounts from t collected dataset. However, as we validate in Section V ne ne Se ne 1, we had to fine-tune these numbers to remove bias and provide a better comparison point with the number of tweets created.

TABLE 2. Sample of tweets sent during the simulation for Scenario 1.

TABLE 4. Sample of tweets sent during the simulation for scenario 2. which reached 31 users, but no engagements. The distribution in scenario 2 is illustrated in Table 4 and Figure 9.

TABLE 3. Sample of belief values from scenario 1.

TABLE 5. Sample of belief values from scenario 2.

descriptionView Paper arrow_downwardDownload

Emotion during election periods: Deciphering Twitter users’ discourse

by Sophia Messini

2024, National Center of Social Research - The Greek Review of Social Research

Within computational political science, a sentiment expressed in social media has been subject to examination about electoral behaviour, more so because of the cases of the successful use of social media by candidates (Obama) or by... more

descriptionView Paper arrow_downwardDownload

El capitalismo de la vigilancia y su influencia en la sociedad de hoy

by Diego Cena

2024

descriptionView Paper arrow_downwardDownload

Emergent local structures in an ecosystem of social bots and humans on Twitter

by Janos Kertesz

2024, EPJ Data Science

Bots in online social networks can be used for good or bad but their presence is unavoidable and will increase in the future. To investigate how the interaction networks of bots and humans evolve, we created six social bots on Twitter... more

descriptionView Paper arrow_downwardDownload

LOS ALGORITMOS DE LAS SOCIEDADES DE CONTROL: POSVERDAD, OPINIÓN PÚBLICA Y MODIFICACIÓN DEL COMPORTAMIENTO HUMANO

by Manuel Álvarez Rufs

2024, TESIS DOCTORAL

Los algoritmos utilizados en las plataformas digitales de las sociedades de control contemporáneas están directamente relacionados con el fenómeno de la posverdad, influyen en la formación de la opinión pública y propician el cambio o la... more

descriptionView Paper arrow_downwardDownload

A python programming widely utilized in the development of a twitter bot as a sophisticated advance technical tool

by Mayank Kumar Tiwari and

2024, International Journal of Computing & Artificial Intelligence

This abstract explores the utilization of Python programming as a pivotal tool in the development of advanced Twitter bots. With the rise of social media automation, Twitter bots have become indispensable for tasks ranging from content... more

descriptionView Paper arrow_downwardDownload

Proceedings of the 3rd International Conference on Natural Language and Speech Processing

by ICNLSP Conference and

2024, Proceedings of the 3rd International Conference on Natural Language and Speech Processing

This volume discusses research and trends in the field of Natural Language Processing and Speech Processing. It covers various topics dealing with building resources, text summarization, spoken language understanding, speech recognition,... more

descriptionView Paper arrow_downwardDownload

A system to secure websites and educate students about cyber security through crowdsourcing

by chitrangi doshi

2024

A System to Secure Websites and Educate Students about Cyber Security through Crowdsourcing Chitrangi Doshi Startups are innovative companies who have ideas for the betterment of the society. But, due to limited resources, and highly... more

descriptionView Paper arrow_downwardDownload

A system to secure websites and educate students about cyber security through crowdsourcing

by chitrangi doshi

2024

descriptionView Paper arrow_downwardDownload

Reverse Engineering the Behaviour of Twitter Bots

by shehu bello

2023, 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS)

Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises... more

descriptionView Paper arrow_downwardDownload

Analysis of 3Vs of Big Data from Fake News and Nigerians’ Consciousness towards National Unity in Times of Uncertainties

by Mutiu Iyanda

2023

Fake news seems to be the monster of the century affecting continents of the world. From Africa to Asia, America to the Himalayas, the impact of fake news on national unity and regional cohesion remains debatable among scholars and... more

descriptionView Paper arrow_downwardDownload

by Rajeev Rajput

2022, Proceedings of the 6th International Conference on Complexity, Future Information Systems and Risk

Online social networks (OSNs) play a significant role during crisis events by offering a convenient channel for information seeking, social bonding, and opinion sharing. In this context, people express their fear, panic, shock, as well as... more

descriptionView Paper arrow_downwardDownload

Bots and political influence: a sociotechnical investigation of social network capital

by Alison Powell

2022, International Journal of Communication

This study explains how bots interact with human users and influence conversational networks on Twitter. We analyze a high-stakes political environment, the UK general election of May 2015, asking human volunteers to tweet from... more

descriptionView Paper arrow_downwardDownload

The Gulf Information War| Propaganda, Fake News, and Fake Trends: The Weaponization of Twitter Bots in the Gulf Crisis

by Marc O Jones

2022, International Journal of Communication

To address the dual need to examine the weaponization of social media and the nature of non-Western propaganda, this article explores the use of Twitter bots in the Gulf crisis that began in 2017. Twitter account-creation dates within... more

Figure 1. Twitter accounts mentioning Qatar by month and year of creation, sampled May 27, 2017.

Figure 2. Twitter accounts mentioning Qatar by month and year of creation, sampled January 1, 2018.

All the infographics had a similar aesthetic quality, containing a limited color palette and lists of various derogatory entries about Qatar. Figure 4 is a typical example of this. It is titled “Qatar Media Snake” and lists numerous journalists and public figures based in Qatar, including Wadah Khanfar, Azmi Bishara, and David Hearst. It is interesting to note that while none of these figures has been singled out in the 13 demands made by the Quartet, all of them work for or have contributed to the outlets singled out in the demands. various derogatory entries about Qatar. Figure 4 is a typical example of this. It is titled “Qatar Media Snake”

Figure 4. Infographic entitled “Qatar Media Snake.”

Figure 5. Tweet containing a screenshot of a fake Reuters article.

Figure 6. Accounts mentioning the hashtag # c#4«_¥ «i @« “(Our hearts are with Tamim but not the two Hamads) by month and year of creation, sampled January 12, 2018. An analysis of the hashtag shows a large spike in account creation in April 2017, when more than 485 accounts were created. Of these, 463 were created on the same day: April 2, 2017.

Most are from Qatar, closely followed by Saudi Arabia. The fact that many of the bots are tweeting from Qatar will likely impact Twitter’s trending algorithm to show that this hashtag is trending in Qatar. The fact that the hashtag was trending in Qatar was used by critics of Qatar to demonstrate Qatari opposition to the “two Hamads.” The tweet shown in Figure 8, from the account Mulaak Mohammed/@Ho0213De (2018), states “praise be to God there is consciousness among some Qataris; they are starting to understand the scum that is the two Hamads.” fact that the hashtag was trending in Qatar was used by critics of Qatar to demonstrate Qatari opposition

Figure 8. Tweet from an account seeking to highlight Qatar’s opposition to the two Hamads by circling the locations of Twitter users (bots).

Saud al-Qahtani was an advisor to the royal court and general supervisor of the Center for Studies and Information Affairs (at the time of writing).” He used similarly manipulated trends in Qatar to indirectly threaten the Qatari authorities and engage in coup-bating (the use of propaganda to encourage regime change). On August 21, 2017, al-Qahtani (2017b) tweeted “The top trend in Qatar now is #LeaveTamim.”® With this tweet, al-Qahtani included a screenshot of Twitter’s trending topics, as if to alleviate any doubt about the veracity of his statement (see Figure 9). 7 Al-Qahtani was demoted following his alleged role in the murder of journalist Jamal Khashoggi

Table 1. Summary of Search Terms and Samples That Form the Basis of the Data for This Article. Note. The hashtags here are certainly not exhaustive. Hundreds of hashtags contaminated by bots existed during the crisis, but for this study, a smaller sample was used to facilitate a more qualitative analysis. * Values are approximate.

Table 3. Thematic Analysis of Bot-Swarm Tweeting on “Al Jazeera Insults King Salman” Hashtag.

descriptionView Paper arrow_downwardDownload

Social Bot Detection on 2019 Indonesia President Candidate’s Supporter’s Tweets

by Pandu Gumelar Pratama

2022, Procedia Computer Science

Nowadays, social media is considered as an essential tool for an organization to communicate with another user, customers and potential customers for gaining popularities, getting ideas and opinion from the users, or affecting another... more

descriptionView Paper arrow_downwardDownload

DARE: Dialogue about Radicalisation and Equality Country level report on drivers of self- radicalisation and digital sociability Greece

by Alexandros Sakellariou

2022

This report examines the drivers of self-radicalisation and digital sociability of the extreme-right in Greece. In the Greek case, the report covers only the extreme right, since the pilot phase of the study demonstrated that there was... more

descriptionView Paper arrow_downwardDownload

Identification of Bots and Cyborgs in the #FeesMustFall Campaign

by Obiseye obiyemi

2022, Informatics

Bots (social robots) are computer programs that replicate human behavior in online social networks. They are either fully automated or semi-automated, and their use makes online activism vulnerable to manipulation. This study examines the... more

Figure 1. The data-driven detection process for the social bots. The total number of tweets is given as:

Figure 2. Monthly tweets between October 2015 and September 2016: (a) lognormal distribution curve and (b) lognormal P-P plot.

Figure 3. Total tweet distribution according to days of the week.

Figure 4. The top ten Twitter users with the highest number of twitter posts, as well as the number of hashtags, URLs, and retweets.

Figure 5. User 1’s frequency, with total tweets per minute over a one-hour period. Figure 4 shows that Users 1 and 2 are the highest-ranking tweeters, and they were among the users identified via the application of methods one (1), two (2), and three (3). Further investigations on the regularity component and the number of tweets sent by these accounts resulted from this. Several tweets for each second as well as 21 tweets in 10 s indicate that the user is self-aware, as shown in Figure 4. Based on the overall 90,783 active accounts, User 1 and User 2 were categorized as bots or cyborgs since they generated roughly 4.57 percent of the 490,449 Twitter posts. Figure 5 depicts the tweeting habits of User 1 and shows a consistent pattern in its tweeting behavior over a 1-h period, with noticeable spikes at 5-min intervals. Hootsuite, a Twitter automation tool, was used mainly by User 1 for regularly tweeting various pieces of material. On 21 October 2015 at 10:53 a.m., the tweeting behavior of User 2, as seen in Figure 6, shows numerous tweets per second for eight consecutive seconds within 10 s. The horizontal axis shows time in the hour:minute:seconds format, while the vertical axis reflects the volume of tweets in that period. The results indicate a high activity level, particularly within 10 s and a minimum of two tweets per second in this dataset. User 2 tweeted using the IFTTT protocol. This is a frequently used technique for both building and generating bot applets.

Figure 6. Volume of User 2’s Twitter posts in a ten-second period.

Table 1. A sample of the data with Tweets and usernames anonymized.

Table 2. Distribution of Tweets by language. Table 3. Distribution of Tweets over the observation period.

Table 4. Results of a descriptive test for total monthly tweets for #FeesMustFall from October 2015 to September 2016. Researchers discovered an unexpected social pattern in the top tweeters’ frequency, volume, and content during the data processing phase that points to automated behavior. Figure 5 shows an example of the tweeting of messages at regular intervals, whereas Figure 6 shows a surge of tweeting activity for a few seconds. Twitter bots and cyborgs

descriptionView Paper arrow_downwardDownload

ABOME: A Multi-platform Data Repository of Artificially Boosted Online Media Entities

by Udit Arora 01

2022

The rise of online media has incentivized users to adopt various unethical and artificial ways of gaining social growth to boost their credibility within a short time period. In this paper, we introduce ABOME, a novel multi-platform data... more

descriptionView Paper arrow_downwardDownload

Extracting Account Attributes for Analyzing Influence on Twitter

by Ola Svenonius

2022, 2019 European Intelligence and Security Informatics Conference (EISIC)

descriptionView Paper arrow_downwardDownload

Tracking Comet ISON through the Twittersphere

by Stuart Palmer

2022, International Journal of Virtual Communities and Social Networking

People are increasingly turning to the Internet and social media for science-related information and communication. Online social media systems are a convenient source of timely and rapid information, including science-related... more

descriptionView Paper arrow_downwardDownload

Middle East Twitter bots and the covid-19 infodemic

by Noura AlJizawi

2022

Misinformation is often found to be propagated by coordinated networks of accounts (‘bots’, ‘sockpuppets’). We looked for such networks on Middle East Twitter by following 149 search filters related to covid-19 during March-April, 2020.... more

descriptionView Paper arrow_downwardDownload

Identification of Bots and Cyborgs in the #FeesMustFall Campaign

by Emmanuel Adetiba, Ph.D

2022, Informatics

descriptionView Paper arrow_downwardDownload

Evidence of complex contagion of information in social media: An experiment using Twitter bots

by Bjarke Mønsted

2022, PLOS ONE

It has recently become possible to study the dynamics of information diffusion in techno-social systems at scale, due to the emergence of online platforms, such as Twitter, with millions of users. One question that systematically recurs... more

Figure 1. Illustration of the status of our botnet at the time of the interventions. The bots had accumulated a large number (~ 25 000) of followers (A) at the time of the interventions (shaded region), and many of the target users followed several distinct bots (B).

Figure 2. Bots in a botnet can work together to provide users with multiple exposures to an intervention. (A) user U only follows bot B;. Bot (B;) acts as a proxy and exposes the user not only to its own content, but also to content from two other bots (Bz and B3), that the user does not follow. (B) Twitter feed from the perspective of user U.

Figure 3. Simple contagion (SC, left) does not adequately describe the contagion dynamics: the best fit underestimates the probability of retweeting after a low number of exposures and overestimates the probability with a large number of exposures. The best fit of complex contagion (CC, right) dynamics correctly estimates the probability of retweeting across the number of sources of exposure. A. Percentage of tweets that were retweeted after k successful exposures (SC) or after exposures from kK sources (CC). B. Number of tweets retweeted following k successful exposures (SC), or after exposures from kK sources (CC). Best fit of SC model (equation 4) and CC model (equation 10) to the data using g = 0.20, plotted up to k =7 (and k = 8) to avoid plotting noisy data for large values of k (and k).

Figure 4. BIC scores for both SC and CC models for a range of values of q, the lower the score the better. Across the values of the g parameter, complex contagion model achieves lower BIC scores than simple contagion. The thick lines are the mean values of the simulations, and the shaded regions are the percentiles corresponding to one standard deviation, i.e. they contain 68% of the simulation results.

Figure 5. Time needed to compute P(k|A) using a brute force approach (solid red line) and our unique subset generation approach (dashed blue line). For each data point, we generated a simulated activity list with length |A| with elements drawn with probabilities based on their frequency in our data, and computed P(xk|A) using the two methods. The runtime is then averaged over 100 such computations in order to minimize noise. Our approach allows us to compute Poisson binomial distributions for activity lists of lengths that would otherwise be infeasible.

descriptionView Paper arrow_downwardDownload

Classification of AI Powered Social Bots on Twitter by Sentiment Analysis and Data Mining through SVM

by touhidur rahaman

2022, International Journal of Computer Applications

In this paper, the behavior of twitter bots and their influence on the social media is investigated. As the user population increased on Twitter, it became an ideal platform for social manipulation and influencing perspectives. There has... more

descriptionView Paper arrow_downwardDownload

Are Bots Humans? Analysis of Bot Accounts in 2019 Indian Lok Sabha Elections (Workshop Paper)

by Aanshul Sadaria

2022, 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM)

Social media platforms have taken political and cultural conversations to an online platform making them more accessible. Ability to anonymously post has allowed more people to participate fearlessly. However, this has also led to an... more

descriptionView Paper arrow_downwardDownload

Automation, Algorithms, and Politics| Bots and Political Influence: A Sociotechnical Investigation of Social Network Capital

by Dhiraj Murthy

2022, International Journal of Communication

descriptionView Paper arrow_downwardDownload

Impact of second-order network motif on online social networks

by Sarbani Roy

2022, The Journal of Supercomputing

The behaviour of individual users in an online social network is a major contributing factor in determining the outcome of multiple network phenomenon. Group formation, growth of the network, information propagation, and rumour blocking... more

descriptionView Paper arrow_downwardDownload

The Influence and Deception of Twitter: The Authenticity of the Narrative and Slacktivism in the Australian Electoral Process

by David M Cook

2022

It is uncertain how many discreet users occupy the social media community. Fake tweets, sock puppets, force‐multipliers and botnets have become embedded within the fabric of new media in sufficient numbers that social media support by... more

descriptionView Paper arrow_downwardDownload

BotNet Detection On Social Media

by ANIKET DEVLE

2022

As the presence of social networks and web services are growing especially with intense competition between the social media sites like Twitter, Instagram, Facebook, etc. It has become an open playground for social bots. These bots not... more

descriptionView Paper arrow_downwardDownload

Automation, Algorithms, and Politics| Bots and Political Influence: A Sociotechnical Investigation of Social Network Capital

by Ramine Tinati

2022, International Journal of Communication

descriptionView Paper arrow_downwardDownload

Understanding the production and circulation of social media data: Towards methodological principles and praxis

by Ramine Tinati

2022, New Media & Society

Social media data have provoked a mixed response from researchers. While there is great enthusiasm for this new source of social data – Twitter data in particular – concerns are also expressed about their biases and unknown provenance... more

descriptionView Paper arrow_downwardDownload

Extensive and Intensive Models of Botnet Influence over Target Audience

by Vladimir Radushevskii

2022, Proceedings of the 2019 International Conference on Pedagogy, Communication and Sociology (ICPCS 2019)

In the article, authors make an overview of existing approaches to typologization of bots and suggest their own approach for distinguishing botnets based on the influence of botnets over target audience. Using the logic of this approach,... more

descriptionView Paper arrow_downwardDownload

Automation, Algorithms, and Politics| Bots and Political Influence: A Sociotechnical Investigation of Social Network Capital

by Susan Halford

2021, International Journal of Communication

descriptionView Paper arrow_downwardDownload

Understanding the production and circulation of social media data: Towards methodological principles and praxis

by Susan Halford

2021, New Media & Society

Figure 2: The Research Data Pipeline Figure 1: Basic Pipeline of Social Media Data Consruction and Circulation

descriptionView Paper arrow_downwardDownload

Automation, Algorithms, and Politics| Bots and Political Influence: A Sociotechnical Investigation of Social Network Capital

by Alison Powell

2021, International Journal of Communication

descriptionView Paper arrow_downwardDownload

Extensive and Intensive Models of Botnet Influence over Target Audience

by Валерия Василькова

2021

descriptionView Paper arrow_downwardDownload

Amplifying influence through coordinated behaviour in social networks

by Derek C Weber

2021, Social Network Analysis and Mining

Political misinformation, astroturfing and organised trolling are online malicious behaviours with significant real-world effects that rely on making the voices of the few sounds like the roar of the many. These are especially dangerous... more

descriptionView Paper arrow_downwardDownload

Information Operations in Turkey: Manufacturing Resilience with Free Twitter Accounts

by Maya Merhi

2021

Social media platforms have more recently shifted towards investigating and reporting on coordinated state-linked manipulation taking place on their sites. Following the 2016 US elections, for instance, Twitter opened their Information... more

Figure 2: Interaction graph between all users in both Twit- ter’s takedown dataset and our collected dataset during the time period where both datasets were active (Jan to Apr 2020). Node/edge colors follow same scheme as Figure 1.

Figure 3: Exemplary structure of main, retweet, backup and sequel accounts.

Table 6: Graph statistics (density, diameter, avg. path length) for Figure | with all nodes, implicit nodes, explicit nodes, and random samples for comparison.

descriptionView Paper arrow_downwardDownload

Impact of second-order network motif on online social networks

by Sankhamita Sinha

2021, The Journal of Supercomputing

descriptionView Paper arrow_downwardDownload

Measuring Reputation and Influence in Online Social Networks: A Systematic Literature Review

by Sami Al-Yazidi

2021, IEEE Access

Online Social Networks (OSNs) are an integral part of the modern lifestyle, and the use of OSN is highly prevalent today. OSNs have enabled the generation of unprecedented quantities of data on users, their interests, relationships,... more

FIGURE 2. Databases that published the articles. FIGURE 1. Study selection process.

FIGURE 5. Quantity of publications per country.

ing, information credibility, human—computer interaction, the social-IoT, anc cyber security. MUHAMMAD AL-QURISHI received the Ph.D. degree from the College of Computer and Information Sciences (CCIS), King Saud University (KSU), Riyadh, Saudi Arabia, in 2017. He is currently a Postdoctoral with the Chair of Pervasive and Mobile Computing (CPMC), CCIS, KSU. He is one of the founding members of CPMC. He has published several articles in ‘efereed journals (IEEE, ACM, Springer, and Wiley). His research interests nclude data science, big data analysis and mining, pervasive computing, and machine-learning. He received the Innovation Award for a mobile cloud serious game from KSU 2013.

descriptionView Paper arrow_downwardDownload

El tótem digital: Bots, Big Data y Tecnocensura

by César A. Rodríguez Cano

2021, La expansión de lo público: indagaciones tecnopolíticas de la sociedad hiperconectada

descriptionView Paper arrow_downwardDownload

Classification of AI Powered Social Bots on Twitter by Sentiment Analysis and Data Mining through SVM

by Abu Foysal

2021, International Journal of Computer Applications

Next, all the tweets are grouped by their twitter handle name and the following features for each twitter account is generated, as shown in Table 1 & Table 2. The user features extracted through the Twitter API are: @handle, total count, followers, following, retweet percentage, hashtags per tweet,

Figure 2: Relationship between retrieved data and total set of data. International Journal of Computer Applications (0975 — 8887) Volume 177 — No. 25, December 2019

the accounts were closed Figure 4: Botometer Classification Results able 3: Comparison between Botometer and SVM Classifier. down so it could not be used in the comparison with full effect. The final result shows, this paper’s classifier has less false positive in compared to Botometer® by OSoMe. Botometer has five false positive out of eight, whereas, SVM classifier has only two.

There are many different approaches towards detecting social automated bots. DeBot [22] is a per-user method with Pearson’s y2 method, which tests the independence of minutes-of-an-hour and seconds-of-a-minute. Limitation of this model is it cannot detect bot accounts with uniformly distributed activities. However, with the proposed model in this paper is using a totally different approach where by using sentiment analysis it is possible to ignore the problem with uniformly distributed activities.

Table 1: Feature extraction from the raw data of suspected Twitter bots. Table 2: Feature extraction from human user accounts.

descriptionView Paper arrow_downwardDownload

Bots, reality shows and Greek political parties: Tracking bots and their political propaganda in Greece

by Dimitris Papaevagelou

2021, Proceedings of the Conference for Truth and Trust Online 2019

descriptionView Paper arrow_downwardDownload

Bots, reality shows and Greek political parties: Tracking bots and their political propaganda in Greece

by Kostas Zafeiropoulos

2021, Proceedings of the Conference for Truth and Trust Online 2019

descriptionView Paper arrow_downwardDownload

Tendencias ciborg y ataques de bots: propaganda computacional, desinformación y polarización política en México

by César A. Rodríguez Cano

2021, Ensayos sobre la comunicación gubernamental en la Cuarta Transformación

descriptionView Paper arrow_downwardDownload

Anonymous Real-Time Analytics Monitoring Solution for Decision Making Supported by Sentiment Analysis

by Robson de Oliveira Albuquerque

2021, Sensors

Currently, social networks present information of great relevance to various government agencies and different types of companies, which need knowledge insights for their business strategies. From this point of view, an important... more

Table 14. Numbers of tweets and retweets by user.

Table 13. Polarity of tweets and retweets. 6.7. Link Analysis

Figure 7. Retweets published by user InfosFutebol. 6.6. Sentiment Analysis

Table 12. Peak polarities of tweets and retweets per day.

Figure 1. OctopusViz architecture. 4.2. Proposed Environment Architecture As a fundamental requirement, and for security and privacy reasons, the environment should ensure that the source of the collection is anonymous in order to not create an opportunity for data change trends or the possibility of influencing the data source. Therefore, one of the ways to achieve this requirement is by using a VPN, so that any collecting sources are not easily identified, avoiding the risk of data contamination by the source. Figure 1 shows the proposed environment’s architecture. The environment’s physical architecture employs a host connected in a Demilitarized Zone (DMZ) and to a protected network of the University of Brasilia (UnB) Research Laboratory. In this host, there are three virtual machines.

Figure 2. Data collected on Twitter between 15 June and 31 July 2018. Histogram with the amount of tweets and retweets collected per day (a). Total amount of tweets and retweets (b). Total number of users and hashtags (c). Figure 2 represents through the visualization layer the total set of data collected by the environment. In Figure 2a, peaks of tweets and retweets that were posted on the Brazilian team match days (June 17th (31,957), June 22th (33,949), June 27th (35,204), July 2nd (34,968) and July 6th (25,506)) can be noticed, the most commented hashtag about the topic in the quarterfinals being detailed in Section 6.8, in Section 6.9, the identification of outliers (users with discrepant activities over a period of time), and in Section 6.10, the analysis of a botnet used to spread tweets. The biggest spike of published tweets and retweets was observed on July 7th (42,733), a day after the quarterfinals (July 6th), the match in which the Brazilian National Soccer Team was eliminated from the FIFA World Cup 2018. On the other hand, there is also a drop after July 10th, indicating that the theme “Brazilian National Soccer Team” was no longer so present on Twitter. It is also possible to identify that 122,975 users posted 730,850 posts and 4240 hashtags (Figure 2b,c).

Figure 3. Data collected on Twitter between 15 June and 31 July 2018. Message classification into tweets and retweets (a). Histogram with the messages’ classification into tweets and retweets collected per day (b). with 35,709 retweets. A difference (29,105 retweets-4647 tweets) also can be noticed on semifinal day (July 10th), when the team that eliminated Brazil in quarterfinals (Belgium) lost to France 1-0.

Figure 4. Cloud of words with the identification from the most referenced hashtags in tweets and retweets

Figure 5. Cloud with the most referenced hashtags. (a) indicates tweets and (b) retweets. Through the interaction provided by the tool, it was possible to apply filters to create and separate hashtags’ clouds by tweets and retweets. It was observed that the most referenced hashtags also depended on analyst interest in tweets (Figure 5a) or retweets (Figure 5b). It may be seen from the first two lines of the data represented in Table 10 that the hashtags #Copa2018 and #BRA were the most commented on for both tweets and retweets. In the third line, it is observed that the hashtags change according to that interest.

Figure 6. Users who posted the most tweets and retweets.

Figure 8. Classification (positive, negative, and neutral) of tweets and retweets per day (a). Classification (positive, negative, and neutral) of tweets and retweets per hour (b). Figures 8-10 indicate user sentiment about the topic “Brazilian National Soccer Team” on eets and retweets between 15 June and 31 July 2018. According to Figure 8a, the highest peak positive-rated tweets and retweets (21,146) came on July 7th, the day after Belgium beat Brazil 2-1 quarterfinals. It can be noted that even losing the match, the users were favorable to the Brazilian m. It is also noted in Figure 8a that the highest peak with negative polarity occurred on June id (13,007) during Round 2 of three of Group E: Brazil 2 x 0 Costa Rica. Probably, this negative ercussion is due to the fact that Brazil tied the match on June 17th during Round 1 of three of oup E: Brazil 1 x 1 Switzerland.

Figure 9. Ranking of tweets and retweets per day with neutral (a), positive (b), and negative (c) polarities.

Figure 10. Overall ranking of tweets and retweets by the algorithm Pattern Analyzer.

Figure 11. Relationship among the entities’ polarity (positive, negative, and neutral) and the user (a). Users who published the most tweets and retweets with positive polarity (b). Link analysis aims to integrate information from various Twitter entities (users, hashtags, tweets, retweets, mentions, sentiment polarity, and images) to debug, organize, and interpret raw data, allowing the analyst to detect existing patterns and connections. Figure 11a presents a graph of the connection between the polarities (positive, negative, and neutral) and the user. For this analysis, we randomly selected 3000 indexed users in the environment. It can be seen from the graph in Figure 11a that more users were related to the neutral and positive polarities. It was also found that several users were related to two or three different polarities (positive, negative, and neutral). In this case, some tweets and retweets of those users were rated as positive and others as negative and neutral.

Figure 12. Relationship between hashtag and user entities (a). Hashtag most referenced in tweets and retweets (b).

Figure 13. Number of users and hashtags (a), tweets and retweets (b). Most commented on hashtag (c). Rating of posts that have been included with that hashtag in tweets and retweets (d). Users who sent the most messages with that hashtag (e). Figure 13. Number of users and hashtags (a), tweets and retweets (b). Most commented on hashtag (c). i On July 6th, during Brazil’s fifth match, in the quarterfinals, the hashtag #Copa2018 stood out on he Dashboard. For more detailed information, a filter was applied to that hashtag. The filter result and s resulting information can be observed as follows: Figure 13a,b shows that 1022 users posted 4098 t i tweets and retweets with that hashtag; another 368 hashtags (Figure 13a) were related to #Copa2018; i can be noted in Figure 13d that 2869 posts with that hashtag were classified as retweets and 1229 as tweets; user torcidasfotos (Figure 13e) was the one who sent the most messages with that hashtag; may be noticed in Figure 14a that 31.92% of users were in favor, 13.88% against, and 54.2% neutral; the hashtag #Copa2018 (Figure 14b) was classified into three different polarities (positive, negative, and neutral); in Figure 14c, it may be spotted that the highest peak of tweets and retweets with that hashtag happened on June 27th (773).

Figure 14. Polarity of tweets and retweets (a). Graph with the relationship between hashtag and polarity entities (b). Histogram with the amount of tweets and retweets collected per day with that hashtag (c). 6.9. Outliers Analysis

Figure 15. Data collected from Twitter between 15 June and 21 June 2018. Discrepant users. For this work, we consider outliers elements those that do not follow a pattern of the set of users to which they were grouped according to the interest criteria analysis. They are users with discrepant activities for a period of time that require special attention as they usually produce values with unreliable effects. On June 21st, before the second match of the Brazilian National Soccer Team in the 2018 FIFA World Cup, it was found that the account dobresdelena presented a great distance from other users, being considered by the analysis an outlier (Figure 15). According to Table 14, users dobresdelena, lorenzopaag, whindersson, cleytu, adrianowilkson, and lacaxarruda) did not post tweets. It was also noted that the user dobresdelena had posted 6723 retweets. A detailed analysis was conducted to try to identify the characteristics of that user.

Figure 16. Dashboard with information about user dobresdelena. Number of hashtags (a), tweets and retweets (b). Discrepant user (c). Number of messages classified as retweets (d). Histogram with the amount of retweets collected per day (e) . Interestingly, all retweets were rated by the Patterns Analyzer algorithm as positive, influencing the analysis of user sentiment regarding “Brazilian National Soccer Team”. Information details may be observed as follows: in Figure 16a, it can be observed that user dobresdelena did not post any hashtag, Figure 16d shows that all posted messages were classified as retweets; it can be noticed that the highest peak of retweets (Figure 16e) happened on June 18th (3917); 100% of the retweets were classified as positives (Figure 17a,b); the highest peak of retweets (374) rated as positive happened on June 17th at 10 p.m. (Figure 17c).

Figure 17. Information about dobresdelena’s retweet polarity (a). Relationship among the entities’ nolarity (nocitive) and the 11cer (h) Claccification (nocitive) of retweete ner hour (c)_

Figure 19. Reverse image analysis with the tools TinEye (a) and Google Images (b).

Figure 20. Analysis through the TweetBotOrNot tool. The tool TweetBotOrNot [52] was also used to analyze the account dobresdelena. This tool uses machine learning to analyze metadata and classify account behavior on Twitter, indicating whether the user is a bot [52] or not. Figure 20 shows that TweetBotOrNot rated the account dobresdelena as a possible bot (0.813).

Table 1. OctopusViz highlighted features compared to related works. 4. Problem Statement and Proposed Solution

Table 3. Guest systems and their settings.

Table 4. Function for translation and correction of tweets.

Table 5. Corpus words stop words and special characters. Table 6. Function for cleaning tweets.

Table 7. Function for tokenization of tweets. 5.3. Phase 3: Classification Sublayer

Table 8. Function for tweets’ classification.

Table 9. The five most referenced hashtags between 15 June and 31 July 2018.

Table 10. Hashtags most referenced by tweets or retweets. 6.5. User Analysis

Table 11. Rating of tweets and retweets by user. The environment also identifies mentions, likes, and hashtags quoted in each tweet and retweet. Four retweets that were posted by user InfosFutebol can be observed in Figure 7. It is interesting to note how many likes (defined by the column favorite_count—14,975, 10,462, 12,679, and 9999) each retweet received. The environment also identifies mentions, likes, and hashtags quoted in each tweet and retweet.

In this scenario, we analyzed dobresdelena’s account on Twitter for relevant details to the interest analysis. Figure 18 shows that at the time of this analysis, the last retweet posted by that user had 36,334 likes. It can be noted that those retweets are always posted at the same time with a variation of seconds (June 17th, 23:56:36, June 18th, 23:56:36, and June 19th, 23:56:25). It can also be identified that in retweets, there is a link (https://t.co/I[YLzqYHXF) featuring three photos of the Brazilian national team goalkeeper, which were used as an account strategy to earn likes.

descriptionView Paper arrow_downwardDownload

Uncovering Social Media Bots: a Transparency-focused Approach

by Lívia Ruback

2021

As the Online Social Networks (OSNs) presence continues to grow as a form of mass communication, tensions regarding their usage and perception by different social groups are reaching a turning point. The number of messages that are... more

descriptionView Paper arrow_downwardDownload

Examining Emergent Communities and Social Bots Within the Polarized Online Vaccination Debate in Twitter

by Ross Schuchard

2021, Social Media + Society

Many states in the United States allow a “belief exemption” for measles, mumps, and rubella (MMR) vaccines. People’s opinion on whether or not to take the vaccine can have direct consequences in public health. Social media has been one of... more

descriptionView Paper arrow_downwardDownload

Twitter Bots

Key research themes

1. How can automated bots on Twitter be accurately detected and classified among benign, malicious, and influence bots?

2. What are the behavioral patterns and roles of social bots in political discourse and disinformation campaigns on Twitter?

3. How do bots interact with humans and influence information ecosystems on Twitter and related platforms?

Related Topics

All papers in Twitter Bots