Project
This page extends the study guide with more information specific to the project work in this course.
Instructions
The following document contains detailed instructions for the project module. It includes the structure of the project, the deliverables you will need to produce throughout the course, guidelines for how to write your post-project paper, as well as detailed assessment criteria.
What? | When? | How? |
---|---|---|
D1 Group contract | 2025-01-31 | Submit on Lisam (as a group) |
D2 Project plan | 2025-02-21 | Submit on Lisam (as a group) |
D3 Title & abstract | 2025-03-13 | Submit via Forms (as a group) |
D4 Presentation | 2025-03-17 — 2025-03-19 | In person |
D5 Peer feedback | 2025-03-17 — 2025-03-19 | In person |
D6 Post-project paper | 2025-03-28 | Submit on Lisam (individually) |
Presentation schedule
Day | Time slot | Presenter | Title | Peer feedback |
---|---|---|---|---|
Monday, 17/3 | 10:20–10:40 | P 01 | Evaluating Bag-of-Words vs. Word Embeddings For Perfume Gender Classification | P 03 |
Monday, 17/3 | 10:40–11:00 | P 02 | Fake News Detection - Comparative study of Naïve Bayes and Logistic Regression | P 04 |
Monday, 17/3 | 11:00–11:20 | P 03 | Predicting song genre based on song lyrics with the use of LSTM and Naive Bayes text classification models | P 01 |
Monday, 17/3 | 11:20–11:40 | P 04 | Fake News: Can a Naive (or not so naive) Bayes Classifier detect false statements in a presidential debate? | P 02 |
Tuesday, 18/3 | 10:20–10:40 | P 06 | Fake News Detection Through Ensemble Voting | P 10 |
Tuesday, 18/3 | 10:40–11:00 | P 07 | Classifying the emotion of twitter posts | P 11 |
Tuesday, 18/3 | 11:00–11:20 | P 14 | Predicting a movie’s genre(s) from its synopsis | P 06 |
Tuesday, 18/3 | 11:20–11:40 | P 10 | A Comparative analysis of Naïve Bayes and SpaCy Models in Detecting AI vs Human Text | P 07 |
Tuesday, 18/3 | 11:40–12:00 | P 11 | Text classification of LiUs party themes | P 14 |
Wednesday, 19/3 | 10:20–10:40 | P 05 | Evaluating tools for text complexity | P 09 |
Wednesday, 19/3 | 10:40–11:00 | P 08 | Predicting literary genres through book summary | P 13 |
Wednesday, 19/3 | 11:00–11:20 | P 09 | Erasing teacher workload: Algorithm for grading essays | P 15 |
Wednesday, 19/3 | 11:20–11:40 | P 13 | Comparing sentiment and irony analysis using VADER and roBERTa | P 05 |
Wednesday, 19/3 | 11:40–12:00 | P 15 | Quantitative Comparison of TF-IDF and Bag-of-Words using Naive Bayes Model on Hate Speech | P 08 |
Discuss your project
You can book a meeting with the examiner to discuss your project, pitch a project idea, or ask any practical questions you as a group might have about the project.
(The booking link is available here throughout the teaching period of this course.)
Slides from the project introduction
Helpful resources
Places to find data
- Kaggle
- HuggingFace Datasets
- Papers With Code
- Riksdagens öppna data (in Swedish)
Software libraries
- spaCy
- NLTK
- trafilatura (for scraping your own text from websites)
- Transformers