Dataset
Project_1_lexicon_and_topic_model
by Ashly Caicedo Cortes AshCaiCor/Project_1_lexicon_and_topic_model
Course: FTEC 6V96 · Financial NLP & Textual Analysis · Author: Ashly Caicedo This project builds a story from two earlier homeworks, HW1 (a data-driven sentiment lexicon compared against TextBlob, VADER and Loughran-McDonald) and HW2 (RBM topic modelling), on…
Dataset Card
Course: FTEC 6V96 · Financial NLP & Textual Analysis · Author: Ashly Caicedo This project builds a story from two earlier homeworks, HW1 (a data-driven sentiment lexicon compared against TextBlob, VADER and Loughran-McDonald) and HW2 (RBM topic modelling), on a dataset of S&P 500, Dow and NASDAQ news headlines. As the assignment requires, it changes the target variable, the tokenization technique and the ML approach, and reports metrics on the train, test and inference partitions. HW1, the lexicon's edge was the market's mood. The custom lexicon beat all three benchmarks on train and test but lost on inference (0.604 vs. 0.623 precision). In October 2020 the market rose on 62% of days, and…
Excerpt from the card by Ashly Caicedo Cortes.
Structure
default 1 rows
| Split | Rows | Size |
|---|---|---|
| train | 1 | 136 B |
Details
- Repository
- AshCaiCor/Project_1_lexicon_and_topic_model
- Publisher
- Ashly Caicedo Cortes
- Task category
- Not stated by the source
- Tags
- Not stated by the source
- Size category
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- a26596a17d00dbe993ac80d5dcc3d9f6af1c60a3
- Last updated
- 2026-09-28
Files
4 files, 1.6 MB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| README.md | Documentation | 13.8 KB | — |
| Project_One_ NLP slides .pdf | Other | 468.8 KB | 1018e227fb7d |
| Project_One_NLP_Lexicon_FINAL_FILE_WITH_THE_RESULTS.ipynb | Other | 1.1 MB | — |
| .gitattributes | Repository | 2.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- No access gate
Released by Ashly Caicedo Cortes through its official repository on Hugging Face.