Personae: a Corpus for Author and Personality Prediction from Text.
Kim LuyckxWalter DaelemansPublished in: LREC (2008)
Keyphrases
- open domain
- writing style
- supervised machine learning
- text data
- broad coverage
- sentence level
- text retrieval
- text corpus
- prediction accuracy
- plain text
- prediction model
- free text
- newspaper articles
- english words
- text processing
- anaphora resolution
- world knowledge
- scientific papers
- text corpora
- natural language text
- prediction error
- keywords
- spontaneous speech
- linguistic information
- document level
- manually annotated
- text collections
- text documents
- information extraction systems
- document corpus
- temporal expressions
- key concepts
- text mining
- entity extraction
- database
- recognizing textual entailment
- topic tracking
- personality traits
- training corpus
- word pairs
- sentiment analysis