An Unsupervised Graph-Based Approach for Detecting Relevant Topics: A Case Study on the Italian Twitter Cohort during the Russia-Ukraine Conflict.
Enrico De SantisAlessio MartinoFrancesca RonciAntonello RizziPublished in: Inf. (2023)
Keyphrases
- emerging topics
- hot topics
- social media
- topic detection
- unsupervised learning
- topic modeling
- highly relevant
- graph structure
- case study
- statistical analysis and data mining
- social networks
- semi supervised
- supervised learning
- lda model
- latent dirichlet allocation
- conflict resolution
- graph theory
- topic discovery
- graph representation
- graph model
- weighted graph
- topic models
- information retrieval
- social networking
- online social networks
- directed graph
- public opinion
- random walk
- information extraction
- trend detection
- search engine