Lexical and Learning-based Emotion Mining from Text
PRESENTER:
Osmar Zaiane
University of Alberta
ABSTRACT:
Emotion mining from text refers to the detection of people's emotions
based on observations of their writings. In this work, we study the
problem of text emotion classification.
First, we collect and cleanse a corpus of Twitter messages that convey at
least one of the targeted emotions, then, we propose several lexical and
learning based methods to
classify the emotion of test tweets and study the effect of different
feature sets. Our experimental results show that a set of Naive Bayes
classifiers, each corresponding to one emotion,
using unigrams as features, is the best performing method for the task. In
addition we test our approach on other datasets, Twitter, and formally
written texts and show that
our approach achieves higher accuracy, compared with state-of-the-art
methods.