Data Science and Text Mining in Urban and Economic Analysis 2400-ENSM122A
Digitization and technological advancement are having a transformative impact on the economy and society. The emergence of online platforms, social media, and AI, among others, is disrupting previous business models and ecosystems. These processes also have a profound impact on cities, urban amenities, and housing markets.
The ongoing digitization and increasing availability of data (e.g., open repositories, APIs, data collected via web scraping) open up new opportunities for conducting empirical analyses and addressing important research questions. Moreover, with the abundance of online text data and the rise of LLMs, the use of text mining and natural language processing (NLP) is opening new research frontiers. At the same time, the state of the art in empirical methods – in econometrics, machine learning, and NLP – is quickly advancing, making it possible to solve novel research problems.
The aim of the seminar is to support the development of master's theses based on modern data sources and employing quantitative methods to analyze topics related to the broadly defined digital economy and urban economics.
Throughout the seminar, key research areas will be discussed, including the economics of digital platforms, urban challenges, real estate markets, online news and social media, and the economics of AI. Potential data sources and methods for acquiring and analyzing them will also be introduced.
Participants will become familiar with the fundamentals of academic research, including how to select relevant literature, conduct literature reviews, ensure the reproducibility of results, and write clear and rigorous academic texts.
Theses in the form of research papers will be encouraged.
Potential Research Areas:
• Urban mobility, micromobility, and city services
• Real estate markets
• Short-term rental market
• Economics of AI
• Online platforms
• E-commerce
• Food delivery sector and restaurants
• Social media and online news
• Cryptocurrency market
Course coordinators
Type of course
Learning outcomes
KNOWLEDGE
• The student understands the fundamentals of sound academic work, including the principles of reproducibility, literature selection, and the structure of a scientific text.
SKILLS
• The student is able to independently prepare a dataset for empirical research.
• The student is familiar with and can effectively use major academic literature databases (e.g., Scopus, Web of Science, Google Scholar).
• The student can independently prepare a literature review, including a critical analysis of sources.
SOCIAL COMPETENCES
• The student understands the ethical principles of data collection, particularly when using methods such as web scraping.
• The student can present the results of their research and formulate and justify conclusions based on data analysis.
Assessment criteria
Semester I – based on an extended thesis proposal
Semester II – based on the completed empirical analysis and
a draft outline of the thesis
Semester III – based on the completed master's thesis