skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Lumen: A machine learning framework to expose influence cues in texts
Phishing and disinformation are popular social engineering attacks with attackers invariably applying influence cues in texts to make them more appealing to users. We introduce Lumen, a learning-based framework that exposes influence cues in text: (i) persuasion, (ii) framing, (iii) emotion, (iv) objectivity/subjectivity, (v) guilt/blame, and (vi) use of emphasis. Lumen was trained with a newly developed dataset of 3K texts comprised of disinformation, phishing, hyperpartisan news, and mainstream news. Evaluation of Lumen in comparison to other learning models showed that Lumen and LSTM presented the best F1-micro score, but Lumen yielded better interpretability. Our results highlight the promise of ML to expose influence cues in text, toward the goal of application in automatic labeling tools to improve the accuracy of human-based detection and reduce the likelihood of users falling for deceptive online content.  more » « less
Award ID(s):
2028734
PAR ID:
10462271
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Frontiers in Computer Science
Volume:
4
ISSN:
2624-9898
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, 2022 IEEE 30th International Requirements Engineering Conference Workshops (REW))
    Abstract—Many organizations use internal phishing campaigns to gauge awareness and coordinate training efforts based on those findings. Ongoing content design is important for phishing training tools due to the influence recency has on phishing susceptibility. Traditional approaches for content development require significant investment and can be prohibitively costly, especially during the requirements engineering phase of software development and for applications that are constantly evolving. While prior research primarily depends upon already known phishing cues curated by experts, our project, Phish Finders, uses crowdsourcing to explore phishing cues through the unique perspectives and thought processes of everyday users in a realistic yet safe online environment, Zooniverse. This paper contributes qualitative analysis of crowdsourced comments that identifies novel cues, such as formatting and typography, which were identified by the crowd as potential phishing indicators. The paper also shows that crowdsourcing may have the potential to scale as a requirements engineering approach to meet the needs of content labeling for improved training tool development. 
    more » « less
  2. ; (, Applied Cognitive Psychology)
    Abstract This study explored how different formats of instructional visuals affect the accuracy of students' metacognitive judgments. Undergraduates (n = 133) studied a series of five biology texts and made judgments of learning. Students were assigned randomly to study the texts only (text only), study the texts with provided visuals (provided visuals group), study the texts and generate their own visuals (learner‐generated visuals group), or study the texts and observe animations of instructor‐generated visuals (instructor‐generated visuals group). After studying the texts and making judgments of learning, all students completed multiple‐choice comprehension tests on each text. The learner‐generated and instructor‐generated visuals groups exhibited significantly higher relative judgment accuracy than the text only and provided visuals groups, though this effect was relatively small. The learner‐generated visuals group also required more study time and was more likely to report the use of visual cues when making their judgments of learning. 
    more » « less
  3. ; ; ; (, Proceedings of the International AAAI Conference on Web and Social Media)
    Recently, deepfake techniques have been adopted by real-world adversaries to fabricate believable personas (posing as experts or insiders) in disinformation campaigns to promote false narratives and deceive the public. In this paper, we investigate how fake personas influence the user perception of the disinformation shared by such accounts. Using Twitter as an exemplary platform, we conduct a user study (N=417) where participants read tweets of fake news with (and without) the presence of the tweet authors' profiles. Our study examines and compares three types of fake profiles: deepfake profiles, profiles of relevant organizations, and simple bot profiles. Our results highlight the significant impact of deepfake and organization profiles on increasing the perceived information accuracy of and engagement with fake news. Moreover, deepfake profiles are rated as significantly more real than other profile types. Finally, we observe that users may like/reply/share a tweet even though they believe it was inaccurate (e.g., for fun or truth-seeking), which could further disseminate false information. We then discuss the implications of our findings and directions for future research. 
    more » « less
  4. ; (, Metacognition and Learning)
    Abstract Prior research suggests most students do not glean valid cues from provided visuals, resulting in reduced metacomprehension accuracy. Across 4 experiments, we explored how the presence of instructional visuals affects students’ metacomprehension accuracy and cue-use for different types of metacognitive judgments. Undergraduates read texts on biology (Study 1a and b) or chemistry (Study 2 and 3) topics, made various judgments (test, explain, and draw) for each text, and completed comprehension tests. Students were randomly assigned to receive only texts (text-only condition) or texts with instructional visualizations (text-and-image condition). In Studies 1b, 2 and 3, students also reported the cues they used to make each judgment. Across the set of studies, instructional visualizations harmed relative metacomprehension accuracy. In Studies 1a and 2, this was especially the case when students were asked to judge how well they felt they could draw the processes described in the text. But in Study 3, this was especially the case when students were asked to judge how well they would do on a set of comprehension tests. In Studies 2 and 3, students who reported basing their judgments on representation-based cues demonstrated more accurate relative accuracy than students who reported using heuristic based cues. Further, across these studies, students reported using visual cues to make their draw judgments, but not their test or explain judgments. Taken together, these results indicate that instructional visualizations can hinder metacognitive judgment accuracy, particularly by influencing the types of cues students use to make judgments of their ability to draw key concepts. 
    more » « less
  5. ; ; ; ; (, Conference on Empirical Methods in Natural Language Processing)
    We present an analytic study on the language of news media in the context of political fact-checking and fake news detection. We compare the language of real news with that of satire, hoaxes, and propaganda to find linguistic characteristics of untrustworthy text. To probe the feasibility of automatic political fact-checking, we also present a case study based on PolitiFact.com using their factuality judgments on a 6-point scale. Experiments show that while media fact-checking remains to be an open research question, stylistic cues can help determine the truthfulness of text. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email