@inproceedings{manoshi-etal-2026-marker,
title = "Marker Signal Void: Linguistic Deception Fingerprinting and Transformer Benchmarking on a Domain-Stratified {B}angla Rumour Corpus",
author = "Manoshi, Farzana Zahid and
Rashid, Sadman Bin and
Anika, Israt Jahan and
Islam, Md. Rakibul",
editor = "Zhang, Chen and
Allaway, Emily and
M{'}hamdi, Meryem and
Limkonchotiwat, Peerat and
Bai, Richard He and
T.Y.S.S., Santosh and
Thapa, Surendrabikram and
Li, Yinqiao",
booktitle = "Proceedings of the 10th Widening {NLP} Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.winlp-main.8/",
pages = "77--86",
ISBN = "979-8-89176-472-9",
abstract = "Rumour detection in Bangla remains severely under-resourced, with prior work conflating it with fake news classification and lacking domain-stratified analysis of the linguistic properties that distinguish misinformation from authentic content. We introduce MisInfo-11K, a domain-stratified corpus of 11,198 instances spanning seven topical domains, constructed from Bangla fact-checking portals and verified news outlets. Using 14 linguistically motivated markers, we show via chi-square and Kruskal-Wallis analysis that 13 of 14 exhibit significant cross-domain variation, revealing distinct deception strategies (e.g., authority mimicry in political rumours, fear amplification in health rumours). Building on this, we introduce the Marker Signal Void (MSV), a chi-square-weighted scoring framework identifying rumour instances with no net discriminative surface signal, establishing Macro-F1 = 0.9843 as the ceiling achievable by this 14-marker set. Benchmarking three pretrained transformers (BanglaBERT, MuRIL, XLM-RoBERTa) against five traditional models, MuRIL achieves the strongest performance (Macro-F1 0.9800), while a marker-augmented Random Forest reaches 0.9750, surpassing XLM-RoBERTa. The gap between the MSV ceiling and transformer performance quantifies the contribution of contextual semantic representations beyond surface-level linguistic cues."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manoshi-etal-2026-marker">
<titleInfo>
<title>Marker Signal Void: Linguistic Deception Fingerprinting and Transformer Benchmarking on a Domain-Stratified Bangla Rumour Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farzana</namePart>
<namePart type="given">Zahid</namePart>
<namePart type="family">Manoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadman</namePart>
<namePart type="given">Bin</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israt</namePart>
<namePart type="given">Jahan</namePart>
<namePart type="family">Anika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Rakibul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Widening NLP Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Allaway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">M’hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">He</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinqiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-472-9</identifier>
</relatedItem>
<abstract>Rumour detection in Bangla remains severely under-resourced, with prior work conflating it with fake news classification and lacking domain-stratified analysis of the linguistic properties that distinguish misinformation from authentic content. We introduce MisInfo-11K, a domain-stratified corpus of 11,198 instances spanning seven topical domains, constructed from Bangla fact-checking portals and verified news outlets. Using 14 linguistically motivated markers, we show via chi-square and Kruskal-Wallis analysis that 13 of 14 exhibit significant cross-domain variation, revealing distinct deception strategies (e.g., authority mimicry in political rumours, fear amplification in health rumours). Building on this, we introduce the Marker Signal Void (MSV), a chi-square-weighted scoring framework identifying rumour instances with no net discriminative surface signal, establishing Macro-F1 = 0.9843 as the ceiling achievable by this 14-marker set. Benchmarking three pretrained transformers (BanglaBERT, MuRIL, XLM-RoBERTa) against five traditional models, MuRIL achieves the strongest performance (Macro-F1 0.9800), while a marker-augmented Random Forest reaches 0.9750, surpassing XLM-RoBERTa. The gap between the MSV ceiling and transformer performance quantifies the contribution of contextual semantic representations beyond surface-level linguistic cues.</abstract>
<identifier type="citekey">manoshi-etal-2026-marker</identifier>
<location>
<url>https://aclanthology.org/2026.winlp-main.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>77</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Marker Signal Void: Linguistic Deception Fingerprinting and Transformer Benchmarking on a Domain-Stratified Bangla Rumour Corpus
%A Manoshi, Farzana Zahid
%A Rashid, Sadman Bin
%A Anika, Israt Jahan
%A Islam, Md. Rakibul
%Y Zhang, Chen
%Y Allaway, Emily
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.Y.S.S., Santosh
%Y Thapa, Surendrabikram
%Y Li, Yinqiao
%S Proceedings of the 10th Widening NLP Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-472-9
%F manoshi-etal-2026-marker
%X Rumour detection in Bangla remains severely under-resourced, with prior work conflating it with fake news classification and lacking domain-stratified analysis of the linguistic properties that distinguish misinformation from authentic content. We introduce MisInfo-11K, a domain-stratified corpus of 11,198 instances spanning seven topical domains, constructed from Bangla fact-checking portals and verified news outlets. Using 14 linguistically motivated markers, we show via chi-square and Kruskal-Wallis analysis that 13 of 14 exhibit significant cross-domain variation, revealing distinct deception strategies (e.g., authority mimicry in political rumours, fear amplification in health rumours). Building on this, we introduce the Marker Signal Void (MSV), a chi-square-weighted scoring framework identifying rumour instances with no net discriminative surface signal, establishing Macro-F1 = 0.9843 as the ceiling achievable by this 14-marker set. Benchmarking three pretrained transformers (BanglaBERT, MuRIL, XLM-RoBERTa) against five traditional models, MuRIL achieves the strongest performance (Macro-F1 0.9800), while a marker-augmented Random Forest reaches 0.9750, surpassing XLM-RoBERTa. The gap between the MSV ceiling and transformer performance quantifies the contribution of contextual semantic representations beyond surface-level linguistic cues.
%U https://aclanthology.org/2026.winlp-main.8/
%P 77-86
Markdown (Informal)
[Marker Signal Void: Linguistic Deception Fingerprinting and Transformer Benchmarking on a Domain-Stratified Bangla Rumour Corpus](https://aclanthology.org/2026.winlp-main.8/) (Manoshi et al., WiNLP 2026)
ACL