spb/uqo-research-db

1% ============================================================================2% UQO Working Paper Template — Economics / Finance3% ============================================================================4\documentclass[12pt,letterpaper]{article}56% --- Encoding & Language ---7\usepackage[utf8]{inputenc}8\usepackage[T1]{fontenc}9\usepackage[english]{babel}1011% --- Page Layout ---12\usepackage[13  letterpaper,14  top=1in,15  bottom=1in,16  left=1in,17  right=1in18]{geometry}1920% --- Typography ---21\usepackage{mathptmx}          % Times-like font (text + math)22\usepackage{microtype}         % Improved typographic refinements23\usepackage{setspace}24\doublespacing                 % double line spacing (working-paper format)2526% --- Math ---27\usepackage{amsmath,amssymb,amsthm}2829% --- Tables ---30\usepackage{booktabs}31\usepackage{tabularx}32\usepackage{multirow}33\usepackage{threeparttable}34\usepackage{siunitx}35\sisetup{36  input-symbols = {()},37  table-format  = -1.3,38  parse-numbers = false39}4041% --- Figures ---42\usepackage{graphicx}43\usepackage{subcaption}44\usepackage{float}4546% --- Colors & Links ---47\usepackage[dvipsnames]{xcolor}48\usepackage[49  colorlinks  = true,50  linkcolor   = NavyBlue,51  citecolor   = NavyBlue,52  urlcolor    = NavyBlue,53  breaklinks  = true54]{hyperref}5556% --- Bibliography ---57\usepackage[authoryear,round,semicolon]{natbib}58\bibliographystyle{aer}5960% --- Captions ---61\usepackage[62  font       = small,63  labelfont  = bf,64  labelsep   = period,65  justification = justified,66  singlelinecheck = false67]{caption}6869% --- Headers & Footers ---70\usepackage{fancyhdr}71\pagestyle{fancy}72\fancyhf{}73\renewcommand{\headrulewidth}{0pt}74\fancyfoot[C]{\thepage}7576% --- Section Formatting ---77\usepackage{titlesec}78\titleformat{\section}{\large\bfseries}{\thesection.}{0.5em}{}79\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection.}{0.5em}{}80\titleformat{\subsubsection}{\normalsize\itshape}{\thesubsubsection.}{0.5em}{}8182% --- Appendix Support ---83\usepackage[toc,page]{appendix}8485% --- Misc ---86\usepackage{enumitem}87\setlist{nosep,leftmargin=*}8889% --- Project-specific additions ---90\graphicspath{{figures/}}91\newcommand{\tstat}[1]{{\footnotesize(\textit{t}=#1)}}9293% ============================================================================94% METADATA — Edit these fields for each working paper95% ============================================================================96\newcommand{\WPnumber}{2026-03}97\newcommand{\WPtitle}{Does the Language of Artificial Intelligence Move Markets?}98\newcommand{\WPsubtitle}{A Semantic Analysis of S\&P~500 SEC Filings and the Cross-Section of Stock Returns, 2010--2026}99\newcommand{\WPdate}{June 2026}100\newcommand{\WPversion}{1.0}101\newcommand{\WPabstract}{%102  We construct a \emph{semantic} measure of artificial-intelligence (AI) engagement for every103  S\&P~500 firm by embedding the text of its annual SEC filings (Form~10-K) with a sentence104  transformer and scoring each passage by cosine similarity to curated AI ``anchor'' concepts:105  internal AI adoption, AI infrastructure exposure, and AI product-disruption risk. Linking these106  scores to monthly equity prices from Yahoo Finance and to the Fama--French factor data, we107  assemble a panel of 7{,}869 firm-years (500 firms, fiscal years 2010--2026) and ask whether the108  intensity of AI language predicts the cross-section of subsequent returns. Our central result is109  \emph{conditional and economically large}: over the full sample the relation is positive but110  modest and only marginally significant, yet after the launch of ChatGPT (November~2022) it more111  than sextuples. The spread between the top and bottom quintile of AI disclosure rises from $+2.4$112  percentage points per year before 2022 to $+14.6$ points afterward, and the long--short Sharpe113  ratio rises from 0.15 to 1.33. The break survives section-weighting choices, alternative signal114  definitions and horizons, dimension reduction, and the exclusion of the ``Magnificent~7''115  mega-caps. Three identification tests sharpen the interpretation: (i)~a placebo across five116  non-AI semantic factors shows the post-2022 jump is specific to AI (ESG and climate disclosure117  earn \emph{negative} post-2022 spreads); (ii)~a market-model event study finds that firms with118  higher pre-event AI disclosure earned $+10.1\%$ higher cumulative abnormal returns over the year119  after ChatGPT ($t=1.97$); and (iii)~the effect is absorbed by firm fixed effects and roughly120  halved by sector fixed effects. We interpret the evidence as an attention- and narrative-driven121  \emph{re-rating}: the market repriced which firms and sectors are AI-exposed once AI became122  salient, rather than rewarding year-to-year changes in wording.%123}124\newcommand{\WPkeywords}{textual analysis, sentence embeddings, artificial intelligence, disclosure, cross-section of returns, investor attention, event study}125\newcommand{\WPjel}{G12, G14, G17, M41, O33}126127% --- Authors ---128\newcommand{\WPauthor}{%129  \begin{tabular}{c}130    {\large Manel Kammoun}\\[-0.05cm]131    {\small\href{mailto:manel.kammoun@uqo.ca}{manel.kammoun@uqo.ca}}\\[0.35cm]132    {\large Djerrycharli Tandjambianda}\\[-0.05cm]133    {\small\href{mailto:djerrycharli.tandjambianda@uqo.ca}{djerrycharli.tandjambianda@uqo.ca}}\\[0.35cm]134    {\large Simon-Pierre Boucher}\\[-0.05cm]135    {\small\href{mailto:simon-pierre.boucher@uqo.ca}{simon-pierre.boucher@uqo.ca}}136  \end{tabular}%137}138\newcommand{\WPaffiliation}{%139  Département des sciences administratives\\140  Université du Québec en Outaouais%141}142\newcommand{\WPemail}{}143\newcommand{\WPaddress}{%144  Gatineau -- Pavillon Alexandre-Taché\\145  283, boulevard Alexandre-Taché\\146  Gatineau, Québec, Canada J9A 1L8%147}148149% ============================================================================150% DOCUMENT151% ============================================================================152\begin{document}153154% --- Title Page ---155\input{sections/titlepage}156157% --- Main Body ---158\input{sections/introduction}159\input{sections/literature}160\input{sections/data}161\input{sections/methodology}162\input{sections/results}163\input{sections/robustness}164\input{sections/discussion}165\input{sections/conclusion}166167% --- References ---168\newpage169\bibliography{references}170171% --- Appendix ---172\input{appendix/appendix}173174\end{document}175