ACL RD-TEC 1.0 Summarization of P06-2081
Paper Title:
WHOSE THUMB IS IT ANYWAY? CLASSIFYING AUTHOR PERSONALITY FROM WEBLOG TEXT
WHOSE THUMB IS IT ANYWAY? CLASSIFYING AUTHOR PERSONALITY FROM WEBLOG TEXT
Authors: Jon Oberlander and Scott Nowson
Primarily assigned technology terms:
- algorithm
- automatic classification
- automatic feature selection
- automatic text classification
- binary classification
- classification
- classifier
- classifiers
- computational linguistics
- computer-mediated communication
- computing
- cross validation
- feature selection
- grouping
- internet
- language processing
- learning
- learning algorithms
- machine learning
- online completion
- personality classification
- processing
- ranking
- rating
- regression
- reporting
- scoring
- search
- sentiment analysis
- sentiment classification
- support vector machines
- text analysis
- text analysis program
- text classification
- text classifier
- validation
- weka
Other assigned terms:
- 10-fold cross validation
- approach
- association for computational linguistics
- bias
- binary classification task
- binary sentiment
- classification accuracy
- classification performance
- classification task
- classification tasks
- computational tractability
- conscientiousness
- corpus frequency
- distribution
- duration
- emotion
- events
- fact
- feature
- feature set
- feature sets
- feature space
- function words
- grammar
- human judgments
- human performance
- implementation
- information gain
- language use
- large feature space
- lexical choice
- lexical research
- linguistic
- linguistic feature
- linguistic features
- linguistics
- log-likelihood
- mood
- n-gram
- n-grams
- ngram
- normal distribution
- opinion
- parts-of-speech
- personality classification performance
- phrase
- relative frequency
- semantic
- sentiment
- statistics
- support vector
- syntactic categories
- term
- test set
- text
- theories
- toolkit
- training
- training data
- word
- word count
- words
