Computational Methods for Text Analysis

2022/2023

Учебный год

ENG

Обучение ведется на английском языке

5

Кредиты

Кто читает:

Департамент социологии

Статус:

Курс по выбору

Когда читается:

3-й курс, 1, 2 модуль

Преподаватель

Пестова Алена Сергеевна

Course Syllabus

Abstract

For social science research, written text provide essential data for studying media and political discourse, ideology, conflict, sentiment and political affiliation and many other things. With a growing availability of larger digital collections of texts it is tempting to scale the research up in terms of the population studied (e.g. “all social media users of a town”), time spans (e.g. “all of the Post-Soviet history”), and geographical scope (e.g. “all educational migration in Russia”). Computational methods for text analysis are expected to help where traditional content analysis is not feasible. During the course we will cover basic word statistics, various exploratory methods, supervised and unsupervised modeling of text phenomena. Data Culture level (0.2.2 — Basic level: Programming + Data Analysis) will be achieved through studying methods of preprocessing and transformation of text data, as well as supervised and unsupervised methods of text analysis, such as topic modeling, classification, semantic analysis.

Learning Objectives

• provide basic understanding on how to properly use collections of texts as quantitative evidence, and to make this knowledge practical

Expected Learning Outcomes

• Being able to adequately interpret and report the results of computational text analysis in research papers.
• Being able to apply computational methods of text analysis (e.g. analysis of word frequency and co-occurrence, document classification, topic modeling) to collections of texts
• Being able to apply word embedding and clustering methods to downstream tasks, such as sentiment analysis, ideological scaling etc.
• Understanding multidimenional representation of lexical meaning and the role of the dimensionality reduction.
• Understanding possibilities of the automated text analysis as well as its pitfalls and important caveats about applying statistical tests to language data.

Course Contents

• Text Prepocessing
• Contrastive Analysis
• Text Classification
• Topic Modelling
• Word Embedding

Assessment Elements

• In-class participation
  In-class practical tasks, paper summaries/presentations
• Final project
  The project is to conduct a completed study using the methods of text analysis studied in this course. The student needs to come up with a research question, collect the necessary data, conduct an analysis and present the study.
• Homeworks

Interim Assessment

• 2022/2023 2nd module
  0.4 * In-class participation + 0.3 * Homeworks + 0.3 * Final project

Bibliography

Recommended Core Bibliography

• Bamman, D., Eisenstein, J., & Schnoebelen, T. (2012). Gender identity and lexical variation in social media. https://doi.org/10.1111/josl.12080
• Jurafsky, D., Chahuneau, V., Routledge, B. R., & Smith, N. A. (2014). Narrative framing of consumer sentiment in online restaurant reviews. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.18543C32

Recommended Additional Bibliography

• Text analysis in R. (2017). Communication Methods and Measures, 11(4), 245–265. https://doi.org/10.1080/19312458.2017.1387238