Natural language processing and text mining¶
Turning free text into something a system can act on: classification and tagging, semantic matching, sentiment, taxonomy induction and extraction from structured documents.
9 supervised theses. See all supervised theses for the full list, or open topics if you are looking for one to take on.
| Level | Author | Title | Date | Industry | Recording |
|---|---|---|---|---|---|
| MSc | I. Viita | Structuring Legacy Data: Classification Pipeline for Construction Industry Archives | May 2026 | video | |
| MSc | O. Lauronen | Unsupervised semantic matching of support tickets | May 2025 | Polycon Oy | |
| MSc | I. Lahtinen | Binary classification of invoice documents based on value added tax | Nov. 2024 | KPMG Oy Ab | |
| MSc | S. Johansson | Classification of purchase invoices to analytic accounts with machine learning | Jan. 2023 | SprintIT | video |
| MSc | R. Hellström | Aspect based sentiment analysis in Finnish | Jan. 2022 | Crowst Oy | |
| MSc | T. Kokkonen | Classifying restaurant menu items with supervised learning | Jan. 2021 | video | |
| MSc | D. Baad | Automatic job skill taxonomy generation for recruitment systems | June 2019 | VXT Research Oy | |
| MSc | L. Kolehmainen | A web scraping system for extracting news articles | Dec. 2019 | Vainu Finland Oy | |
| BSc | N. Erkinheimo | Automated categorization of course feedback using word embeddings | May 2019 |