Propostas submetidas

DEI - FCTUC
Gerado a 2024-11-21 21:23:46 (Europe/Lisbon).
Voltar

Titulo Estágio

MOODoke: Music Emotion Recognition via Natural Language Processing

Áreas de especialidade

Sistemas Inteligentes

Engenharia de Software

Local do Estágio

DEI

Enquadramento

Music emotion-based classification is a research area of increasing interest in Music Information Retrieval (MIR). It has a wide range of applications in fields such us automatic music classification, playlist generation and similarity analysis.
In fact, recent studies identify music emotion as an important criterion used by people in music retrieval and organization. Moreover, music psychology and education acknowledge the emotion component of music as the one most strongly associated with music expressivity.

Objetivo

This thesis has two main objectives:
- Technological objective: update the current MOODoke platform, including current Natural Language Processing (NLP) and machine learning tools to perform lyrics-based emotion variation detection (see moodoke.dei.uc.pt)
- Scientific objective: research new NLP methodologies to improve the existing solution

Plano de Trabalhos - Semestre 1

1. Literature review: music and emotion, NLP and machine learning methodologies
2. Integration of NLP and machine learning code into de current software platform
3. Formulation of research questions
4. Formulation of hypotheses to answer the research questions

Plano de Trabalhos - Semestre 2

5. Development and evaluation of the proposed algorithms and software
6. Thesis writing
7. Possible writing of a scientific research paper

Condições

The MSc candidate will join an active research group, which will give him/her strong scientific support, in an excellent work atmosphere.
Moreover, the candidate will have the opportunity to work in a cutting-edge research area with several open and exciting research possibilities, with plenty of room for scientific innovation.

Orientador

Prof. Dr. Rui Pedro Pinto de Carvalho e Paiva
ruipedro@dei.uc.pt 📩