Linguistic markers of deception in Arabic news headlines: A cross-corpus study of stylistic and numeric features
Eman Salamah Albtoush, Keng Hoon Gan, Saif Addeen A Alrababah · 2026
Read Linguistic markers of deception in Arabic news headlines: A cross-corpus study of stylistic and numeric features by Eman Salamah Albtoush, Keng Hoon Gan, Saif Addeen A Alrababah (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0356823.txt.
Description
Eman Salamah Albtoush, Keng Hoon Gan, and Saif Addeen A Alrababah studied whether deceptive Arabic news headlines betray themselves through style alone. Their 2026 cross-corpus study assembled five headline collections. It added translated English sets, prepared to preserve stylistic flavor. It measured wording and number patterns that differ between fake and genuine headlines.
Modern Arabic language models beat classical text classifiers consistently. They read sub-word patterns that capture both meaning and style. Adding hand-built features on top helped only where fakes leaned on flashy numbers or dates. It added nothing on the combined corpus. Still, the authors value the visible features for explaining a verdict. Pure neural scores cannot do that for editors deciding what to flag.
Catalog record
| CREATOR | Eman Salamah Albtoush, Keng Hoon Gan, Saif Addeen A Alrababah |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 95886 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |