Learning from Earnings Calls: Graph-Based Conversational Modeling for Financial Prediction

References

• Abbasi A, Albrecht C, Vance A, Hansen J (2012) Metafraud: A meta-learning framework for detecting financial fraud. Management Inform. Systems Quart. 36(4):1293–1327.Crossref, Google Scholar
• Abbasi A, Parsons J, Pant G, Sheng ORL, Sarker S (2024) Pathways for design research on artificial intelligence. Inform. Systems Res. 35(2):441–459.Link, Google Scholar
• Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer. Preprint, submitted April 10, https://arxiv.org/abs/2004.05150.Google Scholar
• Bernard VL, Thomas JK (1989) Post-earnings-announcement drift: Delayed price response or risk premium? J. Accounting Res. 27:1–36.Crossref, Google Scholar
• Bian S, Chen Y, Wang X (2022) Manager-analyst interaction quality in earnings conference calls. Preprint, submitted January 4, https://doi.org/10.2139/ssrn.4312025.Google Scholar
• Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J. Machine Learn. Res. 3:993–1022.Google Scholar
• Borochin PA, Cicon JE, DeLisle RJ, Price SM (2018) The effects of conference call tones on market perceptions of value uncertainty. J. Financial Markets 40:75–91.Crossref, Google Scholar
• Boyd-Graber J, Mimno D, Newman D (2014) Care and feeding of topic models: Problems, diagnostics, and improvements. Handbook of Mixed Membership Models and Their Applications.Google Scholar
• Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, et al. (2020) Language models are few-shot learners. Adv. Neural Inform. Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 1877–1901.Google Scholar
• Chen Y, Rui H, Whinston AB (2025) Conversation analytics: Can machines read between the lines in real-time strategic conversations? Inform. Systems Res. 36(1):440–455.Link, Google Scholar
• Chen K, Li X, Luo P, Zhao JL (2021) News-induced dynamic networks for market signaling: Understanding the impact of news on firm equity value. Inform. Systems Res. 32(2):356–377.Link, Google Scholar
• Cheng X, Bala H, Yang M (2024) Engaging users on social media business pages: The roles of user comments and firm responses. Management Inform. Systems Quart. 48(2):731–748.Crossref, Google Scholar
• Cheng Z, Lee D, Tambe P (2022) InnoVAE: Generative AI for mapping patents and firm innovation. Preprint, submitted April 13, https://doi.org/10.2139/ssrn.3868599.Google Scholar
• Cohen L, Lou D, Malloy CJ (2020) Casting conference calls. Management Sci. 66(11):5015–5039.Link, Google Scholar
• Crowley RM, Wong M (2022) Understanding sentiment through context. Working paper, Rotman School of Management, Toronto.Google Scholar
• Denev A, Amen S (2020) The Book of Alternative Data: A Guide for Investors, Traders and Risk Managers (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Dessaint O, Foucault T, Frésard L (2024) Does alternative data improve financial forecasting? The horizon effect. J. Finance 79(3):2237–2287.Crossref, Google Scholar
• Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Annual Conf. North Amer. Chapter Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 4171–4186.Google Scholar
• Dong W, Liao S, Zhang Z (2018) Leveraging financial social media data for corporate fraud detection. J. Management Inform. Systems 35(2):461–487.Crossref, Google Scholar
• Eraker B (2004) Do stock prices and volatility jump? Reconciling evidence from spot and option prices. J. Finance 59(3):1367–1403.Crossref, Google Scholar
• Fama EF, French KR (2015) A five-factor asset pricing model. J. Financial Econom. 116(1):1–22.Crossref, Google Scholar
• Fang X, Gao Y, Hu PJ (2021) A prescriptive analytics method for cost reduction in clinical decision making. MIS Quart. 45(1):83–115.Crossref, Google Scholar
• Fang X, Hu PJH, Li Z, Tsai W (2013) Predicting adoption probabilities in social networks. Inform. Systems Res. 24(1):128–145.Link, Google Scholar
• Foster G, Olsen C, Shevlin T (1984) Earnings releases, anomalies, and the behavior of security returns. Accounting Rev. 59(4):574–603.Google Scholar
• Frankel R, Jennings J, Lee J (2017) Using natural language processing to assess text usefulness to readers: The case of conference calls and earnings prediction. Preprint, submitted February 14, https://doi.org/10.2139/ssrn.3095754.Google Scholar
• Frankel R, Jennings J, Lee J (2022) Disclosure sentiment: Machine learning vs. dictionary methods. Management Sci. 68(7):5514–5532.Link, Google Scholar
• Frankel R, Johnson M, Skinner DJ (1999) An empirical examination of conference calls as a voluntary disclosure medium. J. Accounting Res. 37(1):133–150.Crossref, Google Scholar
• Gentzkow M, Kelly B, Taddy M (2019) Text as data. J. Econom. Literature 57(3):535–574.Crossref, Google Scholar
• Gorodnichenko Y, Pham T, Talavera O (2023) The voice of monetary policy. Amer. Econom. Rev. 113(2):548–584.Crossref, Google Scholar
• Gregor S, Hevner AR (2013) Positioning and presenting design science research for maximum impact. Management Inform. Systems Quart. 37(2):337–355.Crossref, Google Scholar
• Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. Proc. 31st Internat. Conf. Neural Inform. Processing Systems (Curran Associates Inc., Red Hook, NY), 1025–1035.Google Scholar
• Hong LJ, Juneja S, Luo J (2014) Estimating sensitivities of portfolio credit risk using Monte Carlo. INFORMS J. Comput. 26(4):848–865.Link, Google Scholar
• Huang X, Teoh SH, Zhang Y (2014) Tone management. Accounting Rev. 89(3):1083–1113.Crossref, Google Scholar
• Huang AH, Wang H, Yang Y (2023) FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Res. 40(2):806–841.Crossref, Google Scholar
• Huang AH, Lehavy R, Zang AY, Zheng R (2018) Analyst information discovery and interpretation roles: A topic modeling approach. Management Sci. 64(6):2833–2855.Link, Google Scholar
• Huang L, Ma D, Li S, Zhang X, Wang H (2019) Text level graph neural network for text classification. Conf. Empirical Methods Natural Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 3442–3448.Google Scholar
• Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. Fifth Internat. Conf. Learn. Representations (OpenReview.net).Google Scholar
• Kitaev N, Kaiser L, Levskaya A (2020) Reformer: The efficient transformer. Internat. Conf. Learn. Representations (OpenReview.net).Google Scholar
• Kogan S, Meursault V (2021) Corporate disclosure: Facts or opinions? Working Papers 21–40, Federal Reserve Bank of Philadelphia, Philadelphia.Google Scholar
• Kogan S, Levin D, Routledge BR, Sagi JS, Smith NA (2009) Predicting risk from financial reports with regression. Annual Conf. North Amer. Chapter Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 272–280.Google Scholar
• Kothari SP, Li X, Short JE (2009) The effect of disclosures by management, analysts, and business press on cost of capital, return volatility, and analyst forecasts: A study using content analysis. Accounting Rev. 84(5):1639–1670.Crossref, Google Scholar
• Koval R, Andrews N, Yan X (2023) Forecasting earnings surprises from conference call transcripts. Annual Meeting Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 8197–8209.Google Scholar
• Lambert R, Leuz C, Verrecchia RE (2007) Accounting information, disclosure, and the cost of capital. J. Accounting Res. 45(2):385–420.Crossref, Google Scholar
• Li Z, Zhang X, Zhang Y, Long D, Xie P, Zhang M (2023) Towards general text embeddings with multi-stage contrastive learning. Preprint, submitted August 7, https://arxiv.org/abs/2308.03281.Google Scholar
• Liu Y, Pant G, Sheng OR (2020) Predicting labor market competition: Leveraging interfirm network and employee skills. Inform. Systems Res. 31(4):1443–1466.Link, Google Scholar
• Liu J, Wang G, Zhao H, Lu M, Huang L, Chen G (2025) Beyond complements and substitutes: A graph neural network approach for collaborative retail sales forecasting. Inform. Systems Res. 36(4):1993–2016.Abstract, Google Scholar
• Liu NF, Lin K, Hewitt J, Paranjape A, Bevilacqua M, Petroni F, Liang P (2024) Lost in the middle: How language models use long contexts. Trans. Assoc. Comput. Linguistics 12:157–173.Crossref, Google Scholar
• Loughran T, McDonald B (2011) When is a liability not a liability? Textual analysis, dictionaries, and 10-ks. J. Finance 66(1):35–65.Crossref, Google Scholar
• Loughran T, McDonald B (2016) Textual analysis in accounting and finance: A survey. J. Accounting Res. 54(4):1187–1230.Crossref, Google Scholar
• Mastrogiacomo S, Missonier S, Bonazzi R (2014) Talk before it’s too late: Reconsidering the role of conversation in information systems project management. J. Management Inform. Systems 31(1):47–78.Crossref, Google Scholar
• Mayew WJ, Sethuraman M, Venkatachalam M (2020) Individual analysts’ stock recommendations, earnings forecasts, and the informativeness of conference call question and answer sessions. Accounting Rev. 95(6):311–337.Crossref, Google Scholar
• Ng J (2011) The effect of information quality on liquidity risk. J. Accounting Econom. 52(2–3):126–143.Crossref, Google Scholar
• Ouyang S, Zhang Z, Zhao H (2021) Dialogue graph modeling for conversational machine reading. Findings Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 3158–3169.Google Scholar
• Padmanabhan B, Fang X, Sahoo N, Burton-Jones A (2022) Machine learning in information systems research. Management Inform. Systems Quart. 46(1):iii–xix.Crossref, Google Scholar
• Pant G, Sheng OR (2015) Web footprints of firms: Using online isomorphism for competitor identification. Inform. Systems Res. 26(1):188–209.Link, Google Scholar
• Penman SH, Reggiani F, Richardson SA, Tuna A (2015) An accounting-based characteristic model for asset pricing. Preprint, submitted November 30, https://doi.org/10.2139/ssrn.1966566.Google Scholar
• Price SM, Doran JS, Peterson DR, Bliss BA (2012) Earnings conference calls and stock returns: The incremental informativeness of textual tone. J. Banking Finance 36(4):992–1011.Crossref, Google Scholar
• Reimers N, Gurevych I (2019) Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proc. 2019 Conf. Empirical Methods Natural Language Processing and 9th Internat. Joint Conf. Natural Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 3982–3992.Google Scholar
• Rendleman RJ Jr, Jones CP, Latane HA (1982) Empirical anomalies based on unexpected earnings and the importance of risk adjustments. J. Financial Econom. 10(3):269–287.Crossref, Google Scholar
• Rennekamp KM, Sethuraman M, Steenhoven BA (2022) Engagement in earnings conference calls. J. Accounting Econom. 74(1):101498.Crossref, Google Scholar
• Röder M, Both A, Hinneburg A (2015) Exploring the space of topic coherence measures. Internat. Conf. Web Search Data Mining (ACM, New York), 399–408.Google Scholar
• Sang Y, Bao Y (2022a) DialogueGAT: A graph attention network for financial risk prediction by modeling the dialogues in earnings conference calls. Conf. Empirical Methods Natural Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 1623–1633.Google Scholar
• Sang Y, Bao Y (2022b) Predicting corporate risk by jointly modeling company networks and dialogues in earnings conference calls. Preprint, submitted May 25, https://arxiv.org/abs/2206.06174.Google Scholar
• Shi Z, Lee GM, Whinston AB (2016) Toward a better measure of business proximity. Management Inform. Systems Quart. 40(4):1035–1056.Crossref, Google Scholar
• Song Y, Pan S, Liu S, Zhou MX, Qian W (2009) Topic and keyword re-ranking for LDA-based topic modeling. Proc. 18th ACM Conf. Inform. Knowledge Management (ACM, New York), 1757–1760.Google Scholar
• Sridharan SA (2015) Volatility forecasting using financial statement information. Accounting Rev. 90(5):2079–2106.Crossref, Google Scholar
• Sundararajan A, Provost F, Oestreicher-Singer G, Aral S (2013) Research commentary—Information in digital, economic, and social networks. Inform. Systems Res. 24(4):883–905.Link, Google Scholar
• Tam KY, Kiang MY (1992) Managerial applications of neural networks: The case of bank failure predictions. Management Sci. 38(7):926–947.Link, Google Scholar
• Theil CK, Broscheit S, Stuckenschmidt H (2019) PRoFET: Predicting the risk of firms from event transcripts. Internat. Joint Conf. Artificial Intelligence (ijcai.org), 5211–5217.Google Scholar
• Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, et al. (2023) Llama 2: Open foundation and fine-tuned chat models. Preprint, submitted July 18, https://arxiv.org/abs/2307.09288.Google Scholar
• Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Conf. Neural Inform. Processing Systems (Long Beach, CA), vol. 30.Google Scholar
• Verrecchia RE (2001) Essays on disclosure. J. Accounting Econom. 32(1–3):97–180.Crossref, Google Scholar
• Wang K, Ding Y, Han SC (2024) Graph neural networks for text classification: A survey. Artificial Intelligence Rev. 57(8):190.Crossref, Google Scholar
• Wang Z, Jiang C, Zhao H (2023) Depicting risk profile over time: A novel multiperiod loan default prediction approach. Management Inform. Systems Quart. 47(4):1455–1486.Crossref, Google Scholar
• Wang G, Chen G, Zhao H, Zhang F, Yang S, Lu T (2020a) Leveraging multisource heterogeneous data for financial risk prediction: A novel hybrid-strategy-based self-adaptive method. Management Inform. Systems Quart. 45(4):1949–1998.Crossref, Google Scholar
• Wang Z, Wang C, Zhang H, Duan Z, Zhou M, Chen B (2020b) Learning dynamic hierarchical topic graph with graph convolutional network for document classification. Internat. Conf. Artificial Intelligence Statist. (PMLR, New York), 3959–3969.Google Scholar
• Xu P, Chen X, Ma X, Huang Z, Xiang B (2021) Contrastive document representation learning with graph attention networks. Conf. Empirical Methods Natural Language Processing (Association for Computational Linguistics, Stroudsburg, PA), 3874–3884.Google Scholar
• Yang Y, Subramanyam R (2023) Extracting actionable insights from text data: A stable topic model approach. Management Inform. Systems Quart. 47(3):923–954.Crossref, Google Scholar
• Yang Y, Zhang K, Fan Y (2022) Analyzing firm reports for volatility prediction: A knowledge-driven text-embedding approach. INFORMS J. Comput. 34(1):522–540.Link, Google Scholar
• Yang Y, Qin Y, Fan Y, Zhang Z (2023) Unlocking the power of voice for financial risk prediction: A theory-driven deep learning design approach. Management Inform. Systems Quart. 47(1):63–96.Crossref, Google Scholar
• Yang T, Hu L, Shi C, Ji H, Li X, Nie L (2021) HGAT: Heterogeneous graph attention networks for semi-supervised short text classification. ACM Trans. Inform. Systems 39(3):1–29.Crossref, Google Scholar
• Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification. Proc. AAAI Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 7370–7377.Google Scholar
• Yasunaga M, Zhang R, Meelu K, Pareek A, Srinivasan K, Radev D (2017) Graph-based neural multi-document summarization. Conf. Comput. Natural Language Learning (Association for Computational Linguistics, Stroudsburg, PA), 452–462.Google Scholar
• Yates J, Orlikowski WJ (1992) Genres of organizational communication: A structurational approach to studying communication and media. Acad. Management Rev. 17(2):299–326.Crossref, Google Scholar
• Ye Z, Qin Y, Xu W (2021) Financial risk prediction with multi-round Q&A attention network. Proc. Twenty-Ninth Internat. Joint Conf. Artificial Intelligence (Yokohama, Japan), 4576–4582.Google Scholar
• Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J (2019) GNNExplainer: Generating explanations for graph neural networks. Adv. Neural Inform. Processing Systems, vol. 32 (Curran Associates Inc., Red Hook, NY), 9240–9251.Google Scholar
• Yoon J, Pant G, Pant S (2024) Discovery of technological innovation systems: Implications for predicting future innovation. J. Management Inform. Systems. 41(1):39–72.Crossref, Google Scholar
• Zhang Y, Yu X, Cui Z, Wu S, Wen Z, Wang L (2020a) Every document owns its structure: Inductive text classification via graph neural networks. Annual Meeting Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 334–339.Google Scholar
• Zhang Y, Sun S, Galley M, Chen YC, Brockett C, Gao X, Gao J, Liu J, Dolan B (2020b) DIALOGPT: Large-scale generative pre-training for conversational response generation. Annual Meeting Assoc. Comput. Linguistics (Association for Computational Linguistics, Stroudsburg, PA), 270–278.Google Scholar
• Zhao X, Fang X, He J, Huang L (2023) Exploiting expert knowledge for assigning firms to industries: A novel deep learning method. Management Inform. Systems Quart. 47(3):1147–1176.Crossref, Google Scholar
• Zhu Y, Liu X, Sheng ORL (2025) Post-earnings-announcement drift prediction: Leveraging postevent investor responses with multitask learning. Inform. Systems Res. 36(4):2191–2212.Link, Google Scholar