Text Analysis and NLP for Business, Economics and Finance

2026/2027

Учебный год

ENG

Обучение ведется на английском языке

4

Кредиты

Кто читает:

Департамент экономики и анализа данных (Факультет экономики НИУ ВШЭ (Нижний Новгород))

Статус:

Курс по выбору

Когда читается:

3-й курс, 4 модуль

Course Syllabus

Abstract

This course provides an applied introduction to text analysis and Natural Language Processing for students in business, economics, and finance. It focuses on how unstructured textual information from corporate disclosures, policy documents, financial news, social media, investor comments, and business communication can be transformed into structured data for economic and financial analysis. Using Python, students will learn the basic workflow of text data collection, cleaning, preprocessing, keyword extraction, dictionary-based measurement, sentiment analysis, topic discovery, text classification, and simple machine learning applications. The course emphasizes the full research process from formulating a business or economic question to constructing text-based measures and interpreting the results. Through team collaboration and final projects, students will develop the ability to design a small text-as-data project and explain the economic meaning of their findings.

Learning Objectives

• The objective of the course is to introduce students to the use of text analysis and Natural Language Processing methods in business, economics, and finance. The course aims to develop students’ ability to transform unstructured textual information into structured data and to use such data for applied economic and financial analysis. The course focuses on the full workflow of a text-as-data project, including formulating a business or economic question, identifying relevant textual sources, processing raw text, constructing text-based indicators, and interpreting the results. Students will learn how textual data can be used to measure topic exposure, risk, uncertainty, sentiment, tone, and other economically meaningful concepts. The course also aims to develop practical skills in Python-based text analysis. Through online seminars, teamwork assignments, and a final project, students will learn to design and present a small applied text-as-data project and explain the economic meaning, limitations, and validity of their findings.

Expected Learning Outcomes

• Explains the role of textual data in business, economic, financial, and accounting analysis.
• Identifies appropriate textual data sources for applied business, economic, and financial questions.
• Processes raw textual data and transforms it into structured datasets using Python.
• Constructs text-based indicators, including topic exposure, risk, uncertainty, sentiment, and tone measures.
• Evaluates text-based indicators in terms of validity, reproducibility, classification errors, and measurement limitations.
• Develops an applied text-as-data project that includes a research question, textual data source, methodology, findings, and economic interpretation.

Course Contents

• Text and Economic Behavior
• Text Data Sources
• Text Data Processing
• Topic Exposure
• Risk and Uncertainty
• Sentiment and Tone
• Indicator Construction and Validation
• Risk Comparison and Shock Analysis
• Text-Based Variables and Economic Outcomes
• Extended Applications and Course Project

Assessment Elements

• Paper Presentation
  Students work in teams to select and present an academic paper that applies text analysis or NLP methods to a business, economics, finance, or accounting research question. The presentation should summarize the paper’s research question, theoretical motivation, textual data source, sample design, NLP or text-as-data method, construction of text-based variables, validation strategy, main findings, and economic interpretation. Teams should also discuss the paper’s limitations and propose one possible extension or alternative application.
• Text-as-Data Research Proposal
  Students submit an individual research proposal that applies text analysis or NLP methods to a business, economics, finance, or accounting research question. The proposal should clearly define the research question, explain the motivation and expected contribution, identify the textual data source, describe the sample and data collection strategy, specify the NLP or text-as-data method, explain how text-based variables will be constructed and validated, and discuss the feasibility of implementation. The proposal should demonstrate that the project is conceptually meaningful, methodologically appropriate, and practically executable within the available data and technical constraints.
• Class Participation and Seminar Engagement

Interim Assessment

• 2026/2027 4th module
  0.3 * Paper Presentation + 0.2 * Class Participation and Seminar Engagement + 0.5 * Text-as-Data Research Proposal

Bibliography

Recommended Core Bibliography

• 9781491962992 - Bengfort, Benjamin; Bilbro, Rebecca; Ojeda, Tony - Applied Text Analysis with Python : Enabling Language-Aware Data Products with Machine Learning - 2018 - O'Reilly Media - https://search.ebscohost.com/login.aspx?direct=true&db=nlebk&AN=1827695 - nlebk - 1827695
• Benoit, K., Conway, D., Lauderdale, B. E., Laver, M., & Mikhaylov, S. (2016). Crowd-sourced Text Analysis: Reproducible and Agile Production of Political Data. American Political Science Review, (02), 278. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsrep&AN=edsrep.a.cup.apsrev.v110y2016i02p278.295.00
• Grimmer, J., & Stewart, B. M. (2013). Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.BC6A6457
• Hetland, M. L. (2017). Beginning Python : From Novice to Professional (Vol. Third edition). New York: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1174463
• Qualitative text analysis : a guide to methods, practice & using software, Kuckartz, U., 2014
• Text analysis for the social sciences : methods for drawing statistical inferences from texts and transcripts, , 1997
• Text as Data: A New Framework for Machine Learning and the Social Sciences, Grimmer, J., 2022

Recommended Additional Bibliography

• Elfrinkhof, A. van, Maks, I., & Kaal, B. (2014). From Text to Political Positions : Text Analysis Across Disciplines. Amsterdam: John Benjamins Publishing Company. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=761345
• From text to political positions : text analysis across disciplines, , 2014
• Гольдман, А. А. Стратегия и тактика анализа текста: The Strategy and Tactic of Text Analysis : учебное пособие / А. А. Гольдман. — 4-е изд., стер. — Москва : ФЛИНТА, 2024. — 184 с. — ISBN 978-5-9765-2046-2. — Текст : электронный // Лань : электронно-библиотечная система. — URL: https://e.lanbook.com/book/398543 (дата обращения: 00.00.0000). — Режим доступа: для авториз. пользователей.

Authors

• WANG JINHAI