Misinformation on social media undermines informed decision-making and public trust. Prebunking offers a proactive complement by helping users recognize manipulation tactics before they encounter them in the wild. We present CritiSense, a mobile media-literacy app that builds these skills through short, interactive challenges with instant feedback. It is the first multilingual (supporting nine languages) and modular platform, designed for rapid updates across topics and domains. We report a usability study with 93 users: 83.9% expressed overall satisfaction and 90.1% rated the app as easy to use. Qualitative feedback indicates that CritiSense helps improve digital literacy skills. Overall, it provides a multilingual prebunking platform and a testbed for measuring the impact of microlearning on misinformation resilience. Over 6 months, we have reached 500+ active users. It is freely available to all users on the Apple App Store (https://apps.apple.com/us/app/critisense/id6749675792) and Google Play Store (https://play.google.com/store/apps/details?id=com.critisense&hl=en).
Figures & tables
Figure 2: Examples of fictional social media posts, demonstrating different manipulation techniques.
Figure 3: A pictorial example illustrating inoculation theory: expose a weakened misleading message, explain the tactic, then test transfer to a novel post.
Module
EN
AR
BN
FR
HI
IT
TL
NE
UR
Lessons
✓
✓
✓
✓
✓
✓
✓
✓
✓
Quizzes
✓
✓
✓
✓
✓
✓
✓
✓
✓
Detect (text)
✓
✓
Detect (image)
✓
✓
Practice
✓
✓
✓
✓
✓
✓
✓
✓
✓
Table 1: Language coverage and status of the modules. EN=English, AR=Arabic, BN=Bangla, FR=French, HI=Hindi, IT=Italian, TL=Filipino (Tagalog), NE=Nepali, UR=Urdu. ✓ = available; = in progress at the time of writing this paper.
Task/Dataset
Modality
Train
Dev
Test
Factuality (En)
Text
467,830
67,389
134,594
Factuality (Ar)
Text
28,221
4,507
7,847
Propaganda (En)
Text
4,472
621
922
Propaganda (Ar)
Text
18,453
1,318
1,326
ArMeme (Ar)
Image
3,604
522
1,021
Hateful meme (En)
Image
8,500
540
2,000
Table 2: Dataset statistics for each task and modality, showing the number of instances in the train/dev/test splits used in our experiments.
Task/Dataset
Metric
Model
Performance
Factuality (En)
Mi-F1
BERT-Base
0.726
Factuality (Ar)
Mi-F1
AraBERT
0.868
Propaganda (En)
Mi-F1
BERT-Base
0.772
Propaganda (Ar)
Mi-F1
AraBERT
0.762
ArMeme (Ar)
Ma-F1
ViT-B/16
0.554
Hateful meme (En)
Ma-F1
ViT-B/16
0.507
Table 3: Model performance on each task and dataset, reporting the evaluation metric (Micro-F1 for text; Macro-F1 for image) and the backbone used.
Construct
Mean (SD)
α
% Positive
Usability / UX
4.12 (0.85)
0.653
77.4%
Visual Design
4.16 (0.70)
0.774
72.0%
Navigation
4.20 (0.84)
0.837
73.1%
Content Effectiveness
4.09 (0.62)
0.746
65.6%
Behavioral Impact
3.99 (0.72)
0.840
63.4%
Overall (17 items)
—
0.921
—
Table 4: Construct-level summary statistics, including mean ( M ), standard deviation ( SD ), internal consistency ( α ), and the percentage of positive responses. Overall ratings for each questionnaire item in the construct were out of 5.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Construct
#
Description
Usability / UX
2
General usability: capabilities meet needs; ease of use
Visual Design
4
Aesthetics and clarity: design appeal; readability; icon clarity; animation clarity
Navigation
3
Ease of navigation; finding lessons; speed and responsiveness
Content Effectiveness
4
Misinformation identification; example relevance; quiz reinforcement; EN/AR consistency
Table 5: Usability constructs and item counts used in the evaluation.
Figure 4: User satisfaction survey results (N=93). The distribution indicates high platform acceptance, with 83.9% of participants reporting positive sentiment (36.6% Very Satisfied and 47.3% Satisfied). Neutral responses accounted for 11.8%, while combined negative sentiment (Dissatisfied and Very Dissatisfied) remained minimal at 4.4%.
Figure 5: User perception of system usability ( N=93 ). A significant majority (90.1%) expressed agreement, with 60.4% indicating they “Strongly Agree.”