pith. sign in

arxiv: 2406.07293 · v2 · submitted 2024-06-11 · 💻 cs.SI

Automated versus Human Engagement: Mapping Cognitive Bias Triggers in Online Discourse

Lynnette Hui Xian Ng , Wenqi Zhou , Kathleen M. Carley This is my paper

Pith reviewed 2026-05-24 00:04 UTC · model grok-4.3

classification 💻 cs.SI
keywords cognitive biasesbotssocial media engagementCOVID-19information diffusionheuristicsautomated accountscomputational social science
0
0 comments X

The pith

Bots embed cognitive bias triggers more frequently than humans, producing source-dependent effects on engagement in online discourse.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper builds a computational framework that identifies triggers for eight cognitive biases through data proxies in 3.5 million COVID-19 posts. Automated accounts deploy these triggers more often than human users. In bot posts, affective and stance-shifting triggers link to higher engagement while authority and repetition cues link to lower engagement. Stacking multiple triggers reduces engagement for bot content but leaves human-authored posts unaffected.

Core claim

Automated accounts embed these triggers more frequently than human users, yielding distinctly source-dependent associations with audience interaction. In bot-authored posts, affective and cognitive dissonance (stance-shifting) triggers are strongly associated with higher engagement, while the deployment of authority and availability (repetition) cues correlates with reduced audience interaction. Positive engagement correlations with bot-authored content declines when multiple biases are stacked within a single post, whereas human-authored communication remains structurally resilient to high trigger density.

What carries the argument

A computational framework that detects triggers for eight cognitive biases via observable data proxies in social media posts.

If this is right

  • Bots use bias triggers more often than humans across contested narratives.
  • Affective and stance-shifting triggers raise engagement for bot posts.
  • Authority and repetition triggers lower engagement for bot posts.
  • High trigger density reduces engagement only in bot content.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Bias trigger patterns could serve as additional signals for automated account detection on platforms.
  • Human content may maintain reach under conditions that penalize automated accounts.
  • The source-dependent patterns may generalize to other contested topics.

Load-bearing premise

The chosen observable data proxies accurately and specifically capture instances of the eight distinct cognitive biases without substantial misclassification or unaccounted confounds from post content or platform algorithms.

What would settle it

Hand annotation of a random sample of posts to measure agreement between the proxy detections and direct judgments of bias trigger presence.

Figures

Figures reproduced from arXiv: 2406.07293 by Kathleen M. Carley, Lynnette Hui Xian Ng, Wenqi Zhou.

Figure 1
Figure 1. Figure 1: Overview of Dataset Formation Methodology. This figure illustrates the pipeline of data collection and filtering. The data was collected when the platform was named ”Twitter”. 4 Dataset Formation To study the techniques used in the spread of misinformation via triggers of cognitive biases, we constructed our own dataset, the Misinfo Dataset [PITH_FULL_IMAGE:figures/full_fig_p009_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Distribution of the Bias Triggers in Tweets. This illustrates the percentage of tweets that attempted to trigger cognitive biases by two different user types. For example, 62.08% of Bot tweets triggered Availability Bias, and 34.41% of them triggered Cognitive Dissonance 6 Analysis and Results 6.1 Presence of Bias Triggers in Misinformation Tweets In this subsection, we provide an overview of the identifie… view at source ↗
Figure 3
Figure 3. Figure 3: Co-Occurrence of Bias Triggers in Misinfo Tweets. The heatmap is colored according to the prevalence of triggers of two biases occurring in the same misinformation tweet. 6.2 Bias and Engagement We evaluated the differential association between triggers of biases and the persuasion of misinformation tweets. We adopted tweet engagement metrics as a measure of persuasiveness, following past work where persua… view at source ↗
Figure 4
Figure 4. Figure 4: Engagement by Bias Triggers. This presents the proportion of engagement from tweets associated with triggers of a given bias over the total engagement from all tweets authored by Bots and Humans, respectively. For example, Bot tweets with Affect/Negativity Bias triggers receive 29.95% of the total favorite counts in the Misinfo Dataset. more conversational and effort-demanding engagement (i.e., reply) than… view at source ↗
Figure 5
Figure 5. Figure 5: Relation between the Number of Biases Triggered and Engagement This figure illustrates the relationship between the number of biases triggered and the engagement of tweet. The Number of Triggered Biases and Engagement Finally, we visualized the correla￾tion between the number of biases that a tweet attempted to trigger versus its engagement in [PITH_FULL_IMAGE:figures/full_fig_p021_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustrated Summary of the Association between Bias Triggers and Misin￾formation Tweet Engagement Note: Red color indicates a negative association, green color indicates a positive association, and black color indicates no correlation. 22 [PITH_FULL_IMAGE:figures/full_fig_p022_6.png] view at source ↗
Figure 1
Figure 1. Figure 1 [PITH_FULL_IMAGE:figures/full_fig_p025_1.png] view at source ↗
Figure 5
Figure 5. Figure 5 [PITH_FULL_IMAGE:figures/full_fig_p026_5.png] view at source ↗
read the original abstract

In the digital environment, human attention is frequently guided by cognitive heuristics rather than deliberate evaluation. Since low-credibility narratives often lack substantive factual evidence, their diffusion disproportionally relies on activating these mental shortcut to simulate credibility and capture attention. This study presents a computational framework designed to detect computational triggers through observable data proxies for eight distinct cognitive biases across 3.5 million posts of contested COVID-19 narratives. We demonstrate that automated accounts (bots) embed these triggers more frequently than human users, yielding distinctly source-dependent associations with audience interaction. In bot-authored posts, affective and cognitive dissonance (stance-shifting) triggers are strongly associated with higher engagement, while the deployment of authority and availability (repetition) cues correlates with reduced audience interaction. Furthermore, we identify limits to heuristic compounding: positive engagement correlations with bot-authored content declines when multiple biases are stacked within a single post, whereas human-authored communication remains structurally resilient to high trigger density. By operationalizing psychological heuristics into scalable, measurable data, this work bridges computational social science and cognitive psychology to reveal how source identity (bot/human) shapes the mechanics of information diffusion in digital networks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents a computational framework using observable data proxies to detect triggers for eight cognitive biases across 3.5 million posts on contested COVID-19 narratives. It claims bots embed these triggers more frequently than humans, with source-dependent engagement effects (affective and cognitive dissonance triggers linked to higher engagement in bots; authority and availability cues to lower engagement) and limits to heuristic compounding (declining positive correlations for bots at high trigger density, but resilience in human-authored content).

Significance. If the proxies accurately capture the biases without substantial misclassification, the work offers a scalable bridge between computational social science and cognitive psychology by quantifying how source identity shapes heuristic use in information diffusion on contested topics.

major comments (2)
  1. [Abstract] Abstract: the central claims on frequency differences, engagement correlations, and heuristic compounding rest on the unvalidated mapping of posts to the eight biases via 'observable data proxies'; no inter-rater reliability, precision/recall benchmarks against human coders, or ablation against alternative codings are reported, rendering the associations uninterpretable if proxies conflate content features with the intended biases.
  2. [Abstract] Abstract: the reported source-dependent associations with audience interaction lack any mention of statistical controls for confounds (e.g., post length, topic, timing, or platform algorithms), so it is unclear whether the distinct bot vs. human patterns are attributable to the bias triggers or to unmodeled factors.
minor comments (1)
  1. [Abstract] Abstract: the data collection details (source platform, exact time window, bot-detection method) are omitted, which would be needed for reproducibility even if the proxy validation is added.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback, which identifies key areas for strengthening the manuscript. We address the concerns about proxy validation and statistical controls point by point below, outlining revisions that will improve the rigor of the reported associations while maintaining the framework's core contributions.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claims on frequency differences, engagement correlations, and heuristic compounding rest on the unvalidated mapping of posts to the eight biases via 'observable data proxies'; no inter-rater reliability, precision/recall benchmarks against human coders, or ablation against alternative codings are reported, rendering the associations uninterpretable if proxies conflate content features with the intended biases.

    Authors: We acknowledge that the current manuscript relies on observable data proxies derived from established psychological literature without reporting formal validation metrics such as inter-rater reliability or precision/recall. The proxies map specific linguistic and structural features (e.g., emotional valence indicators for affective triggers) directly to bias triggers. To address this limitation, the revised manuscript will add a dedicated validation subsection. This will include human coding of a stratified sample of posts, computation of inter-rater reliability (Cohen's kappa), precision/recall against proxy labels, and an ablation comparing our feature set to alternative codings. These additions will clarify the mapping's reliability. revision: yes

  2. Referee: [Abstract] Abstract: the reported source-dependent associations with audience interaction lack any mention of statistical controls for confounds (e.g., post length, topic, timing, or platform algorithms), so it is unclear whether the distinct bot vs. human patterns are attributable to the bias triggers or to unmodeled factors.

    Authors: We agree that the absence of explicit controls for potential confounds limits causal attribution of the engagement patterns. The current analysis compares bot and human posts but does not detail multivariate adjustments. In revision, we will augment the engagement models with regression specifications that include controls for post length (token count), timing (temporal fixed effects), topic (via topic modeling or content categories), and account metadata. We will also explicitly discuss limitations related to unobservable platform algorithms. These changes will isolate the contribution of the bias triggers more clearly. revision: yes

Circularity Check

0 steps flagged

No significant circularity; empirical measurement on external data

full rationale

The paper presents a computational framework that applies observable data proxies to detect eight cognitive bias triggers in 3.5 million posts, then reports empirical frequencies, source-dependent engagement associations, and density interactions. No equations, first-principles derivations, fitted parameters renamed as predictions, or uniqueness theorems appear in the provided text. Central claims rest on direct measurement rather than any self-definitional reduction or self-citation chain. This is a standard empirical analysis with no load-bearing steps that reduce to the paper's own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central framework rests on the domain assumption that the selected observable proxies validly and specifically detect the eight named cognitive biases. No free parameters or invented entities are referenced in the abstract.

axioms (1)
  • domain assumption Observable data proxies accurately represent the eight cognitive biases
    This assumption underpins the entire computational detection framework described in the abstract.

pith-pipeline@v0.9.0 · 5732 in / 1318 out tokens · 27412 ms · 2026-05-24T00:04:45.696501+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

142 extracted references · 142 canonical work pages · 1 internal anchor

  1. [1]

    Cognitive attraction and online misinformation

    Alberto Acerbi. Cognitive attraction and online misinformation. Palgrave Communications, 5 0 (1), 2019

    work page 2019

  2. [2]

    Benevolent deception in human computer interaction

    Eytan Adar, Desney S Tan, and Jaime Teevan. Benevolent deception in human computer interaction. In Proceedings of the SIGCHI conference on human factors in computing systems, pages 1863--1872, 2013

    work page 2013

  3. [3]

    People are strange when you're a stranger: Impact and influence of bots on social networks

    Luca Maria Aiello, Martina Deplano, Rossano Schifanella, and Giancarlo Ruffo. People are strange when you're a stranger: Impact and influence of bots on social networks. In Proceedings of the international AAAI conference on web and social media, volume 6, pages 10--17, 2012

    work page 2012

  4. [4]

    Fake news, disinformation and misinformation in social media: a review

    Esma A \" meur, Sabrine Amri, and Gilles Brassard. Fake news, disinformation and misinformation in social media: a review. Social Network Analysis and Mining, 13 0 (1): 0 30, 2023

    work page 2023

  5. [5]

    Lies kill, facts save: Detecting covid-19 misinformation in twitter

    Mabrook S Al-Rakhami and Atif M Al-Amri. Lies kill, facts save: Detecting covid-19 misinformation in twitter. Ieee Access, 8: 0 155961--155970, 2020

    work page 2020

  6. [6]

    Viral news on social media

    Ahmed Al-Rawi. Viral news on social media. Digital journalism, 7 0 (1): 0 63--79, 2019

    work page 2019

  7. [7]

    Fake news and covid-19: modelling the predictors of fake news sharing among social media users

    Oberiri Destiny Apuke and Bahiyah Omar. Fake news and covid-19: modelling the predictors of fake news sharing among social media users. Telematics and Informatics, 56: 0 101475, 2021

    work page 2021

  8. [8]

    Information overload and misinformation sharing behaviour of social media users: Testing the moderating role of cognitive ability

    Oberiri Destiny Apuke, Bahiyah Omar, Elif Asude Tunca, and Celestine Verlumun Gever. Information overload and misinformation sharing behaviour of social media users: Testing the moderating role of cognitive ability. Journal of Information Science, page 01655515221121942, 2022

    work page 2022

  9. [9]

    P astel Q A non - G N E T --- gnet-research.org

    Marc-André Argentino. P astel Q A non - G N E T --- gnet-research.org. https://gnet-research.org/2021/03/17/pastel-qanon/, 2021. [Accessed 12-02-2024]

    work page 2021

  10. [10]

    Detection of spammers in twitter marketing: a hybrid approach using social media analytics and bio inspired computing

    Reema Aswani, Arpan Kumar Kar, and P Vigneswara Ilavarasan. Detection of spammers in twitter marketing: a hybrid approach using social media analytics and bio inspired computing. Information Systems Frontiers, 20: 0 515--530, 2018

    work page 2018

  11. [11]

    Tiktok, twitter, and platform-specific technocultural discourse in response to taylor swift’s lgbtq+ allyship in ‘you need to calm down’

    Melissa K Avdeeff. Tiktok, twitter, and platform-specific technocultural discourse in response to taylor swift’s lgbtq+ allyship in ‘you need to calm down’. Contemporary music review, 40 0 (1): 0 78--98, 2021

    work page 2021

  12. [12]

    Bot-hunter: a tiered approach to detecting & characterizing automated activity on twitter

    David M Beskow and Kathleen M Carley. Bot-hunter: a tiered approach to detecting & characterizing automated activity on twitter. In Conference paper. SBP-BRiMS: International conference on social computing, behavioral-cultural modeling and prediction and behavior representation in modeling and simulation, volume 3, 2018

    work page 2018

  13. [13]

    Tweet, tweet, retweet: Conversational aspects of retweeting on twitter

    Danah Boyd, Scott Golder, and Gilad Lotan. Tweet, tweet, retweet: Conversational aspects of retweeting on twitter. In 2010 43rd Hawaii international conference on system sciences, pages 1--10. IEEE, 2010

    work page 2010

  14. [14]

    Bias in algorithmic filtering and personalization

    Engin Bozdag. Bias in algorithmic filtering and personalization. Ethics and information technology, 15: 0 209--227, 2013

    work page 2013

  15. [15]

    Developing persuasive systems for marketing: the interplay of persuasion techniques, customer traits and persuasive message design

    Annye Braca and Pierpaolo Dondio. Developing persuasive systems for marketing: the interplay of persuasion techniques, customer traits and persuasive message design. Italian Journal of Marketing, 2023 0 (3): 0 369--412, 2023

    work page 2023

  16. [16]

    Weaponized health communication: Twitter bots and russian trolls amplify the vaccine debate

    David A Broniatowski, Amelia M Jamison, SiHua Qi, Lulwah AlKulaib, Tao Chen, Adrian Benton, Sandra C Quinn, and Mark Dredze. Weaponized health communication: Twitter bots and russian trolls amplify the vaccine debate. American journal of public health, 108 0 (10): 0 1378--1384, 2018

    work page 2018

  17. [17]

    The interplay of online network homogeneity, populist attitudes, and conspiratorial beliefs: Empirical evidence from a survey on german facebook users

    Manuel Cargnino. The interplay of online network homogeneity, populist attitudes, and conspiratorial beliefs: Empirical evidence from a survey on german facebook users. International Journal of Public Opinion Research, 33 0 (2): 0 337--353, 2021

    work page 2021

  18. [18]

    Social cybersecurity: an emerging science

    Kathleen M Carley. Social cybersecurity: an emerging science. Computational and mathematical organization theory, 26 0 (4): 0 365--381, 2020

    work page 2020

  19. [19]

    Ora & netmapper

    L Richard Carley, Jeff Reminga, and Kathleen M Carley. Ora & netmapper. In International conference on social computing, behavioral-cultural modeling and prediction and behavior representation in modeling and simulation. Springer, volume 3, page 7, 2018

    work page 2018

  20. [20]

    Give me more feedback: Annotating argument persuasiveness and related attributes in student essays

    Winston Carlile, Nishant Gurrapadi, Zixuan Ke, and Vincent Ng. Give me more feedback: Annotating argument persuasiveness and related attributes in student essays. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 621--631, 2018

    work page 2018

  21. [21]

    Social network behavior and public opinion manipulation

    Long Chen, Jianguo Chen, and Chunhe Xia. Social network behavior and public opinion manipulation. Journal of Information Security and Applications, 64: 0 103060, 2022

    work page 2022

  22. [22]

    Persuasion strategies of misinformation-containing posts in the social media

    Sijing Chen, Lu Xiao, and Jin Mao. Persuasion strategies of misinformation-containing posts in the social media. Information Processing & Management, 58 0 (5): 0 102665, 2021 a

    work page 2021

  23. [23]

    Neutral bots probe political bias on social media

    Wen Chen, Diogo Pacheco, Kai-Cheng Yang, and Filippo Menczer. Neutral bots probe political bias on social media. Nature communications, 12 0 (1): 0 5580, 2021 b

    work page 2021

  24. [24]

    Spam article detection on social media platform using deep learning: Enhancing content integrity and user experience

    Panuwat Chiawchansilp and Pittipol Kantavat. Spam article detection on social media platform using deep learning: Enhancing content integrity and user experience. In Proceedings of the 13th International Conference on Advances in Information Technology, pages 1--6, 2023

    work page 2023

  25. [25]

    From curious hashtags to polarized effect: profiling coordinated actions in indonesian twitter discourse

    Adya Danaditya, Lynnette Hui Xian Ng, and Kathleen M Carley. From curious hashtags to polarized effect: profiling coordinated actions in indonesian twitter discourse. Social Network Analysis and Mining, 12 0 (1): 0 105, 2022

    work page 2022

  26. [26]

    How celebrities feed tweeples with personal and promotional tweets: Celebrity twitter use and audience engagement

    Sanchari Das, Javon Goard, and Dakota Murray. How celebrities feed tweeples with personal and promotional tweets: Celebrity twitter use and audience engagement. In Proceedings of the 8th International Conference on Social Media & Society, \#SMSociety17, New York, NY, USA, 2017. Association for Computing Machinery. https://isbnsearch.org/isbn/9781450348478...

    work page doi:10.1145/3097286.3097316 2017

  27. [27]

    A perfect storm: social media news, psychological biases, and ai

    Pratim Datta, Mark Whitmore, and Joseph K Nwankpa. A perfect storm: social media news, psychological biases, and ai. Digital Threats: Research and Practice, 2 0 (2): 0 1--21, 2021

    work page 2021

  28. [28]

    Detecting bots and assessing their impact in social networks

    Nicolas Guenon des Mesnards, David Scott Hunter, Zakaria el Hjouji, and Tauhid Zaman. Detecting bots and assessing their impact in social networks. Operations research, 70 0 (1): 0 1--22, 2022

    work page 2022

  29. [29]

    The art and science of persuasion: not all crowdfunding campaign videos are the same

    Sanorita Dey, Brittany Duff, Karrie Karahalios, and Wai-Tat Fu. The art and science of persuasion: not all crowdfunding campaign videos are the same. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, pages 755--769, 2017

    work page 2017

  30. [30]

    Political persuasion on social media: Tracing direct and indirect effects of news use and social interaction

    Trevor Diehl, Brian E Weeks, and Homero Gil de Z \'u \ n iga. Political persuasion on social media: Tracing direct and indirect effects of news use and social interaction. New media & society, 18 0 (9): 0 1875--1895, 2016

    work page 2016

  31. [31]

    Social media engagement behavior: A framework for engaging customers through social media content

    Rebecca Dolan, Jodie Conduit, Catherine Frethey-Bentham, John Fahy, and Steve Goodman. Social media engagement behavior: A framework for engaging customers through social media content. European journal of marketing, 53 0 (10): 0 2213--2243, 2019

    work page 2019

  32. [32]

    Like, share, comment, and repeat: far-right messages, emotions, and amplification in social media

    Larissa Doroshenko and Fangjing Tu. Like, share, comment, and repeat: far-right messages, emotions, and amplification in social media. Journal of Information Technology & Politics, 20 0 (3): 0 286--302, 2023

    work page 2023

  33. [33]

    Retweet us, we will retweet you: Spotting collusive retweeters involved in blackmarket services

    Hridoy Sankar Dutta, Aditya Chetan, Brihi Joshi, and Tanmoy Chakraborty. Retweet us, we will retweet you: Spotting collusive retweeters involved in blackmarket services. In 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pages 242--249. IEEE, 2018

    work page 2018

  34. [34]

    Twibot-22: Towards graph-based twitter bot detection

    Shangbin Feng, Zhaoxuan Tan, Herun Wan, Ningnan Wang, Zilong Chen, Binchi Zhang, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, et al. Twibot-22: Towards graph-based twitter bot detection. Advances in Neural Information Processing Systems, 35: 0 35254--35269, 2022

    work page 2022

  35. [35]

    Online misinformation: Challenges and future directions

    Miriam Fernandez and Harith Alani. Online misinformation: Challenges and future directions. In Companion Proceedings of the The Web Conference 2018, pages 595--602, 2018

    work page 2018

  36. [36]

    Global risks report 2024

    World Economic Forum. Global risks report 2024. https://www.weforum.org/publications/global-risks-report-2024/, 01 2024. [Accessed 17-01-2024]

    work page 2024

  37. [37]

    Truth as social practice in a digital era: iteration as persuasion

    Clare LE Foster. Truth as social practice in a digital era: iteration as persuasion. AI & SOCIETY, 38 0 (5): 0 2009--2023, 2023

    work page 2009

  38. [38]

    Social media overload, exhaustion, and use discontinuance: Examining the effects of information overload, system feature overload, and social overload

    Shaoxiong Fu, Hongxiu Li, Yong Liu, Henri Pirkkalainen, and Markus Salo. Social media overload, exhaustion, and use discontinuance: Examining the effects of information overload, system feature overload, and social overload. Information Processing & Management, 57 0 (6): 0 102307, 2020

    work page 2020

  39. [39]

    Estimating the bot population on twitter via random walk based sampling

    Mei Fukuda, Kazuki Nakajima, and Kazuyuki Shudo. Estimating the bot population on twitter via random walk based sampling. IEEE Access, 10: 0 17201--17211, 2022

    work page 2022

  40. [40]

    Unsupervised fake news detection: A graph-based approach

    Siva Charan Reddy Gangireddy, Deepak P, Cheng Long, and Tanmoy Chakraborty. Unsupervised fake news detection: A graph-based approach. In Proceedings of the 31st ACM conference on hypertext and social media, pages 75--83, 2020

    work page 2020

  41. [41]

    Do socialbots dream of popping the filter bubble? the role of socialbots in promoting deliberative democracy in social media

    Timothy Graham and Robert Ackland. Do socialbots dream of popping the filter bubble? the role of socialbots in promoting deliberative democracy in social media. In Socialbots and Their Friends, pages 203--222. Routledge, 2016

    work page 2016

  42. [42]

    Social bots: Human-like by means of human control? Big data, 5 0 (4): 0 279--293, 2017

    Christian Grimme, Mike Preuss, Lena Adam, and Heike Trautmann. Social bots: Human-like by means of human control? Big data, 5 0 (4): 0 279--293, 2017

    work page 2017

  43. [43]

    Changing perspectives: Is it sufficient to detect social bots? In Social Computing and Social Media

    Christian Grimme, Dennis Assenmacher, and Lena Adam. Changing perspectives: Is it sufficient to detect social bots? In Social Computing and Social Media. User Experience and Behavior: 10th International Conference, SCSM 2018, Held as Part of HCI International 2018, Las Vegas, NV, USA, July 15-20, 2018, Proceedings, Part I 10, pages 445--461. Springer, 2018

    work page 2018

  44. [44]

    Fake news on twitter during the 2016 us presidential election

    Nir Grinberg, Kenneth Joseph, Lisa Friedland, Briony Swire-Thompson, and David Lazer. Fake news on twitter during the 2016 us presidential election. Science, 363 0 (6425): 0 374--378, 2019

    work page 2016

  45. [45]

    Misinformation, disinformation, and online propaganda

    Andrew M Guess and Benjamin A Lyons. Misinformation, disinformation, and online propaganda. Social media and democracy: The state of the field, prospects for reform, 10, 2020

    work page 2020

  46. [46]

    Jing Guo and Hsuan-Ting Chen. How does multi-platform social media use lead to biased news engagement? examining the role of counter-attitudinal incidental exposure, cognitive elaboration, and network homogeneity. Social Media+ Society, 8 0 (4): 0 20563051221129140, 2022

    work page 2022

  47. [47]

    Which argument is more convincing? analyzing and predicting convincingness of web arguments using bidirectional lstm

    Ivan Habernal and Iryna Gurevych. Which argument is more convincing? analyzing and predicting convincingness of web arguments using bidirectional lstm. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1589--1599, 2016

    work page 2016

  48. [48]

    Perceived experts are prevalent and influential within an antivaccine community on twitter

    Mallory J Harris, Ryan Murtfeldt, Shufan Wang, Erin A Mordecai, and Jevin D West. Perceived experts are prevalent and influential within an antivaccine community on twitter. PNAS nexus, 3 0 (2): 0 pgae007, 2024

    work page 2024

  49. [49]

    For who page? tiktok creators’ algorithmic dependencies

    Laura Herman. For who page? tiktok creators’ algorithmic dependencies. 2023

    work page 2023

  50. [50]

    Toward a synthesis of cognitive biases: how noisy information processing can bias human decision making

    Martin Hilbert. Toward a synthesis of cognitive biases: how noisy information processing can bias human decision making. Psychological bulletin, 138 0 (2): 0 211, 2012

    work page 2012

  51. [51]

    Bots and misinformation spread on social media: Implications for covid-19

    McKenzie Himelein-Wachowiak, Salvatore Giorgi, Amanda Devoto, Muhammad Rahman, Lyle Ungar, H Andrew Schwartz, David H Epstein, Lorenzo Leggio, and Brenda Curtis. Bots and misinformation spread on social media: Implications for covid-19. Journal of medical Internet research, 23 0 (5): 0 e26933, 2021

    work page 2021

  52. [52]

    Emotions: The unexplored fuel of fake news on social media

    Christy Galletta Horner, Dennis Galletta, Jennifer Crawford, and Abhijeet Shirsat. Emotions: The unexplored fuel of fake news on social media. Journal of Management Information Systems, 38 0 (4): 0 1039--1066, 2021

    work page 2021

  53. [53]

    Narrative persuasion in social media: an empirical study of luxury brand advertising

    Ran Huang, Sejin Ha, and Sun-Hwa Kim. Narrative persuasion in social media: an empirical study of luxury brand advertising. Journal of Research in Interactive Marketing, 12 0 (3): 0 274--292, 2018

    work page 2018

  54. [54]

    Persuasive impact of online media: investigating the influence of visual persuasion

    Nurulhuda Ibrahim, Kok Wai Wong, and Mohd Fairuz Shiratuddin. Persuasive impact of online media: investigating the influence of visual persuasion. In 2015 Asia Pacific Conference on Multimedia and Broadcasting, pages 1--7. IEEE, 2015

    work page 2015

  55. [55]

    Tracking china’s cross-strait bot networks against taiwan

    Charity S Jacobs, Lynnette Hui Xian Ng, and Kathleen M Carley. Tracking china’s cross-strait bot networks against taiwan. In International conference on social computing, behavioral-cultural modeling and prediction and behavior representation in modeling and simulation, pages 115--125. Springer, 2023

    work page 2023

  56. [56]

    It takes two to negotiate: Modeling social exchange in online multiplayer games

    Kokil Jaidka, Hansin Ahuja, and Lynnette Ng. It takes two to negotiate: Modeling social exchange in online multiplayer games. arXiv preprint arXiv:2311.08666, 2023

    work page arXiv 2023

  57. [57]

    Adapting and extending a typology to identify vaccine misinformation on twitter

    Amelia Jamison, David A Broniatowski, Michael C Smith, Kajal S Parikh, Adeena Malik, Mark Dredze, and Sandra C Quinn. Adapting and extending a typology to identify vaccine misinformation on twitter. American Journal of Public Health, 110 0 (S3): 0 S331--S339, 2020

    work page 2020

  58. [58]

    Fndnet--a deep convolutional neural network for fake news detection

    Rohit Kumar Kaliyar, Anurag Goswami, Pratik Narang, and Soumendu Sinha. Fndnet--a deep convolutional neural network for fake news detection. Cognitive Systems Research, 61: 0 32--44, 2020

    work page 2020

  59. [59]

    Duped by bots: why some are better than others at detecting fake social media personas

    Ryan Kenny, Baruch Fischhoff, Alex Davis, Kathleen M Carley, and Casey Canfield. Duped by bots: why some are better than others at detecting fake social media personas. Human factors, 66 0 (1): 0 88--102, 2024

    work page 2024

  60. [60]

    On the complementarity of images and text for the expression of emotions in social media

    Anna Khlyzova, Carina Silberer, and Roman Klinger. On the complementarity of images and text for the expression of emotions in social media. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 1--15, 2022

    work page 2022

  61. [61]

    Tackling misinformation with games: a systematic literature review

    Kristian Kiili, Juho Siuko, and Manuel Ninaus. Tackling misinformation with games: a systematic literature review. Interactive Learning Environments, pages 1--16, 2024

    work page 2024

  62. [62]

    Rumor has it: The effects of virality metrics on rumor believability and transmission on twitter

    Ji Won Kim. Rumor has it: The effects of virality metrics on rumor believability and transmission on twitter. New Media & Society, 20 0 (12): 0 4807--4825, 2018

    work page 2018

  63. [63]

    Confirmation, disconfirmation, and information in hypothesis testing

    Joshua Klayman and Young-Won Ha. Confirmation, disconfirmation, and information in hypothesis testing. Psychological review, 94 0 (2): 0 211, 1987

    work page 1987

  64. [64]

    Social media analytics for stance mining a multi-modal approach with weak supervision

    Sumeet Kumar. Social media analytics for stance mining a multi-modal approach with weak supervision. PhD thesis, Ph. D. thesis, Carnegie Mellon University, 2020

    work page 2020

  65. [65]

    Homophily and minority-group size explain perception biases in social networks

    Eun Lee, Fariba Karimi, Claudia Wagner, Hang-Hyun Jo, Markus Strohmaier, and Mirta Galesic. Homophily and minority-group size explain perception biases in social networks. Nature human behaviour, 3 0 (10): 0 1078--1087, 2019

    work page 2019

  66. [66]

    Correcting vaccine misinformation on social media: the inadvertent effects of repeating misinformation within such corrections on covid-19 vaccine misperceptions

    Jiyoung Lee and Kim Bissell. Correcting vaccine misinformation on social media: the inadvertent effects of repeating misinformation within such corrections on covid-19 vaccine misperceptions. Current Psychology, pages 1--13, 2024

    work page 2024

  67. [67]

    Countering misinformation and fake news through inoculation and prebunking

    Stephan Lewandowsky and Sander Van Der Linden. Countering misinformation and fake news through inoculation and prebunking. European Review of Social Psychology, 32 0 (2): 0 348--384, 2021

    work page 2021

  68. [68]

    Social bots sour activist sentiment without eroding engagement

    Linda Li, Orsolya Vasarhelyi, and Balazs Vedres. Social bots sour activist sentiment without eroding engagement. arXiv preprint arXiv:2403.12904, 2024

    work page arXiv 2024

  69. [69]

    Accuracy prompts protect professional content moderators from the illusory truth effect, Mar 2024

    Hause Lin, Marlyn T Savio, Xieyining Huang, Miriah Steiger, Rachel Guevara, Dali Szostak, Gordon Pennycook, and David G Rand. Accuracy prompts protect professional content moderators from the illusory truth effect, Mar 2024. URL osf.io/preprints/psyarxiv/gswm6

    work page 2024

  70. [70]

    Social media and credibility indicators: The effect of influence cues

    Xialing Lin, Patric R Spence, and Kenneth A Lachlan. Social media and credibility indicators: The effect of influence cues. Computers in human behavior, 63: 0 264--271, 2016

    work page 2016

  71. [71]

    Botmoe: Twitter bot detection with community-aware mixtures of modal-specific experts

    Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, and Minnan Luo. Botmoe: Twitter bot detection with community-aware mixtures of modal-specific experts. arXiv preprint arXiv:2304.06280, 2023

    work page arXiv 2023

  72. [72]

    Retweet if you please! do news factors explain engagement? Journal of Marketing Communications, 24 0 (4): 0 375--392, 2018

    Luc \' a Manzanaro, Carmen Valor, and Juan Diego Paredes-G \'a zquez. Retweet if you please! do news factors explain engagement? Journal of Marketing Communications, 24 0 (4): 0 375--392, 2018

    work page 2018

  73. [73]

    Bot, or not? comparing three methods for detecting social bots in five political discourses

    Franziska Martini, Paul Samula, Tobias R Keller, and Ulrike Klinger. Bot, or not? comparing three methods for detecting social bots in five political discourses. Big data & society, 8 0 (2): 0 20539517211033566, 2021

    work page 2021

  74. [74]

    Rtbust: Exploiting temporal patterns for botnet detection on twitter

    Michele Mazza, Stefano Cresci, Marco Avvenuti, Walter Quattrociocchi, and Maurizio Tesconi. Rtbust: Exploiting temporal patterns for botnet detection on twitter. In Proceedings of the 10th ACM conference on web science, pages 183--192, 2019

    work page 2019

  75. [75]

    Misinformation more likely to use non-specific authority references: Twitter analysis of two covid-19 myths

    Joseph McGlynn, Maxim Baryshevtsev, and Zane A Dayton. Misinformation more likely to use non-specific authority references: Twitter analysis of two covid-19 myths. Harvard Kennedy School Misinformation Review, 1 0 (3), 2020

    work page 2020

  76. [76]

    A cultural paradox in authority-based advertising

    Jae Min Jung, Kawpong Polyorat, and James J Kellaris. A cultural paradox in authority-based advertising. International Marketing Review, 26 0 (6): 0 601--632, 2009

    work page 2009

  77. [77]

    Collective attention in the age of (mis) information

    Delia Mocanu, Luca Rossi, Qian Zhang, Marton Karsai, and Walter Quattrociocchi. Collective attention in the age of (mis) information. Computers in Human Behavior, 51: 0 1198--1204, 2015

    work page 2015

  78. [78]

    A confirmation bias view on social media induced polarisation during covid-19

    Sachin Modgil, Rohit Kumar Singh, Shivam Gupta, and Denis Dennehy. A confirmation bias view on social media induced polarisation during covid-19. Information Systems Frontiers, pages 1--25, 2021

    work page 2021

  79. [79]

    The disaster of misinformation: a review of research in social media

    Sadiq Muhammed T and Saji K Mathew. The disaster of misinformation: a review of research in social media. International journal of data science and analytics, 13 0 (4): 0 271--285, 2022

    work page 2022

  80. [80]

    Covid-twitter-bert: A natural language processing model to analyse covid-19 content on twitter

    Martin M \"u ller, Marcel Salath \'e , and Per E Kummervold. Covid-twitter-bert: A natural language processing model to analyse covid-19 content on twitter. Frontiers in Artificial Intelligence, 6: 0 1023281, 2023

    work page 2023

Showing first 80 references.