Text and Image Mining for Business Research

Time and place: April 2022

Learning goal and objectives:

The objective of this course is to enhance students’ knowledge on how to use text mining methods, processes, and tools for business research with a focus in marketing and management. In addition to text, the last part of the course will involve work with image mining. The learning goal is to prepare students for the conceptual and empirical challenges involved in the use of unstructured data (i.e., text and images) for business research. The course will cover topics such as theories of language and semiotics, measurement error, validation, machine learning, and endogeneity issues.

Instruction and examination:

The course is built on prior reading of recent guides and empirical applications of text and image mining, and hands-on work on class examples based on recent datasets from Twitter, Instagram, TripAdvisor, and Yelp.

The course will cover four main units:

  1. An Introduction to Methods and Theories for Unstructured Data
  2. Dictionary Methods
  3. Machine/Deep Learning (supervised and unsupervised)
  4. Multimodality and Image Measurement.

The course involves theory sessions, hands-on examples guide (carried out in parallel with the student), individual applications and post discussion/consultations. The course will be helpful for doctoral students’ decision-making concerning data gathering, measurement, modelling, and manuscript positioning.

Credits: 4 ECTS

Grading: The course will be graded as Pass or Fail. There will be an exam at the end of the course and an individual project that will be carried out through the course.

Prerequisites: Programing and basic statistical knowledge is recommended. The course will use Knime Analytics as the main analytics software, together with limited integrations of R and Python. Students attending to the course will need to install all required software and extension before attending (instructions will be provided). A laptop computer with at least 8GB RAM is recommended to run the analyses.


  • Max. 25 students are admitted to the course.
  • Application guidelines:  PhD. students in all fields of economics and business studies, (e.g., in marketing, management, accounting, etc.). As most of the literature and examples relate to marketing and management, the priority will be given to doctoral students who are majoring in those disciplines. Participants can apply by sending their CV and a motivation letter to Robert Ciuchita ( robert.ciuchita@hanken.fi).
  • Last application date: 17.12.2021
  • Notification of acceptance: 17.01.2022


Francisco Villarroel Ordenes, Assistant Professor of Marketing, Luiss Guido Carli (https://impresaemanagement.luiss.it/docenti/cv/354198).

Dr. Francisco Villarroel Ordenes is an Assistant Professor of Marketing at the LUISS Guido Carli University, in Rome (Italy). His work has centered on the phenomenon of unstructured data (e.g., consumer reviews, social media images, discussion forums) and their business implications. Francisco has substantial expertise in the use of linguistic theory and text mining methods to develop accurate metrics of online consumers’ sentiment, brand content strategies, and employee perceptions, assessing their business impact on customer satisfaction, word of mouth and sales. Francisco’s publications have appeared in the Journal of Consumer Research, Journal of Service Research, Journal of Retailing, Journal of Business Research and Journal of Advertising, amongst others. Currently, Francisco regularly teaches “Business and Marketing Analytics” and “Marketing Metrics” at LUISS Guido Carli University, and a Summer School on Text Mining Methods at the University of Calabria, Italy.

Course coordinator and contact information:

Robert Ciuchita, Assistant Professor, Department of Marketing, Hanken School of Economics

robert.ciuchita@hanken.fi; +358 (0)50 414 3557