We are the NLP-UMUTeam, a research group at the University of Murcia (Spain) focused on Natural Language Processing (NLP) for Spanish and multilingual settings.
We frequently participate in shared tasks and evaluation campaigns (SemEval, IberLEF, CLEF, etc.), and we publish in international journals and conferences on NLP and language technologies.
Our main research lines include:
- Text classification & author profiling
- Hate & hope speech detection (Spanish and multilingual)
- Sentiment & emotion analysis (text and multimodal speech–text)
- Misinformation, satire and political communication
- Clinical NLP and domain-specific resources for Spanish
| Area | Repository | What it contains |
|---|---|---|
| Multimodal emotion | multimodal-emotion-analysis-dataset | Spanish MEACorpus 2023: multimodal speech-text emotion corpus and baseline models. |
| Hate speech (MTL) | mtl-hatespeech-spanish | MTLHateCorpus 2023: dataset and code for multi-task hate speech detection in Spanish. |
| Political ideology | FGCS-political-ideology-2021 | Code for predicting political ideology from Spanish politicians' tweets. |
| Humor & offense | hahackathon-2021 | SemEval-2021 Task 7: humor and offense detection. |
👉 For a full list of repositories, see the Repositories tab.
- 🐦 Twitter/X: @nlp_umuteam
- 📧 Contact: valencia@um.es