@inproceedings{sachdeva-dasgupta-2026-words,
title = "When Words Move Markets: Sentiment and Semantic Complexity in Central Bank Communication and Equity Volatility",
author = "Sachdeva, Arush and
Dasgupta, Anirban",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.23/",
pages = "274--312",
ISBN = "979-8-89176-466-8",
abstract = "Central bank communications influence market expectations, but their linguistic attributes are inadequately examined in emerging markets. We examine 337 Reserve Bank of India Monetary Policy Committee documents (2010{--}2025) and relate their textual features to minute-level and daily volatility in NIFTY indices. Our load-bearing result concerns sentiment. Within a pre-specified nine-test confirmatory family, negative-sentiment probability is associated with event-window equity volatility and CLS-based sentiment with event-window turbulence in India VIX; both survive Benjamini{--}Hochberg correction, rank correlation, bootstrap intervals and regime-conditional controls, both strengthen under a time-matched volatility baseline, and both outperform a Loughran{--}McDonald lexicon on an identical sample. The sentiment model is a fine-tuned FinBERT that we validate directly on human-annotated central-bank text (81.3{\%} accuracy, macro-$F_1 = 0.784$, Cohen{'}s $\kappa = 0.714$ against a human majority vote). Semantic complexity, measured with the DAST framework, plays a secondary, construct-level role: it is largely orthogonal to classical readability ($|r|_{\max}=0.21$) but behaves as an ordinal measure of generated semantic structure, and at the daily horizon a sentiment$\times$complexity interaction yields only small exploratory in-sample gains that are not significant under heteroskedasticity-robust inference and do not improve out-of-sample prediction, even after controlling for document length. A third candidate, attention concentration, is Bonferroni-significant under Pearson correlation yet reverses sign under Spearman and has a bootstrap interval spanning zero; we report it as a cautionary methodological result rather than a finding. A pre-specified February 20 Chow test and an endogenous break search near March 11, 2020 indicate pronounced COVID-period regime dependence. Overall, textual features add in-sample explanatory power over a GARCH plus policy-rate baseline but no incremental out-of-sample predictive value on any index."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sachdeva-dasgupta-2026-words">
<titleInfo>
<title>When Words Move Markets: Sentiment and Semantic Complexity in Central Bank Communication and Equity Volatility</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arush</namePart>
<namePart type="family">Sachdeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirban</namePart>
<namePart type="family">Dasgupta</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Central bank communications influence market expectations, but their linguistic attributes are inadequately examined in emerging markets. We examine 337 Reserve Bank of India Monetary Policy Committee documents (2010–2025) and relate their textual features to minute-level and daily volatility in NIFTY indices. Our load-bearing result concerns sentiment. Within a pre-specified nine-test confirmatory family, negative-sentiment probability is associated with event-window equity volatility and CLS-based sentiment with event-window turbulence in India VIX; both survive Benjamini–Hochberg correction, rank correlation, bootstrap intervals and regime-conditional controls, both strengthen under a time-matched volatility baseline, and both outperform a Loughran–McDonald lexicon on an identical sample. The sentiment model is a fine-tuned FinBERT that we validate directly on human-annotated central-bank text (81.3% accuracy, macro-F₁ = 0.784, Cohen’s ąppa = 0.714 against a human majority vote). Semantic complexity, measured with the DAST framework, plays a secondary, construct-level role: it is largely orthogonal to classical readability (|r|_\max=0.21) but behaves as an ordinal measure of generated semantic structure, and at the daily horizon a sentiment\timescomplexity interaction yields only small exploratory in-sample gains that are not significant under heteroskedasticity-robust inference and do not improve out-of-sample prediction, even after controlling for document length. A third candidate, attention concentration, is Bonferroni-significant under Pearson correlation yet reverses sign under Spearman and has a bootstrap interval spanning zero; we report it as a cautionary methodological result rather than a finding. A pre-specified February 20 Chow test and an endogenous break search near March 11, 2020 indicate pronounced COVID-period regime dependence. Overall, textual features add in-sample explanatory power over a GARCH plus policy-rate baseline but no incremental out-of-sample predictive value on any index.</abstract>
<identifier type="citekey">sachdeva-dasgupta-2026-words</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.23/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>274</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Words Move Markets: Sentiment and Semantic Complexity in Central Bank Communication and Equity Volatility
%A Sachdeva, Arush
%A Dasgupta, Anirban
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F sachdeva-dasgupta-2026-words
%X Central bank communications influence market expectations, but their linguistic attributes are inadequately examined in emerging markets. We examine 337 Reserve Bank of India Monetary Policy Committee documents (2010–2025) and relate their textual features to minute-level and daily volatility in NIFTY indices. Our load-bearing result concerns sentiment. Within a pre-specified nine-test confirmatory family, negative-sentiment probability is associated with event-window equity volatility and CLS-based sentiment with event-window turbulence in India VIX; both survive Benjamini–Hochberg correction, rank correlation, bootstrap intervals and regime-conditional controls, both strengthen under a time-matched volatility baseline, and both outperform a Loughran–McDonald lexicon on an identical sample. The sentiment model is a fine-tuned FinBERT that we validate directly on human-annotated central-bank text (81.3% accuracy, macro-F₁ = 0.784, Cohen’s ąppa = 0.714 against a human majority vote). Semantic complexity, measured with the DAST framework, plays a secondary, construct-level role: it is largely orthogonal to classical readability (|r|_\max=0.21) but behaves as an ordinal measure of generated semantic structure, and at the daily horizon a sentiment\timescomplexity interaction yields only small exploratory in-sample gains that are not significant under heteroskedasticity-robust inference and do not improve out-of-sample prediction, even after controlling for document length. A third candidate, attention concentration, is Bonferroni-significant under Pearson correlation yet reverses sign under Spearman and has a bootstrap interval spanning zero; we report it as a cautionary methodological result rather than a finding. A pre-specified February 20 Chow test and an endogenous break search near March 11, 2020 indicate pronounced COVID-period regime dependence. Overall, textual features add in-sample explanatory power over a GARCH plus policy-rate baseline but no incremental out-of-sample predictive value on any index.
%U https://aclanthology.org/2026.finnlp-1.23/
%P 274-312
Markdown (Informal)
[When Words Move Markets: Sentiment and Semantic Complexity in Central Bank Communication and Equity Volatility](https://aclanthology.org/2026.finnlp-1.23/) (Sachdeva & Dasgupta, FinNLP 2026)
ACL