Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models

Emotion classification can benefit from a larger pool of training data but manually expanding the emotion corpus is labour-intensive and time-consuming. Distant supervision can be used to collect large amount of training data in a short period of time using emotion word hashtags, but the collecte...

Full description

Bibliographic Details
Main Author: Yong, Kuan Shyang
Format: Thesis
Language:English
Published: 2022
Subjects:
Online Access:http://eprints.usm.my/59117/
http://eprints.usm.my/59117/1/YONG%20KUAN%20SHYANG%20-%20TESIS.pdf
_version_ 1848884089732464640
author Yong, Kuan Shyang
author_facet Yong, Kuan Shyang
author_sort Yong, Kuan Shyang
building USM Institutional Repository
collection Online Access
description Emotion classification can benefit from a larger pool of training data but manually expanding the emotion corpus is labour-intensive and time-consuming. Distant supervision can be used to collect large amount of training data in a short period of time using emotion word hashtags, but the collected data may contain excessive noise. In this research, we proposed a text augmentation strategy to efficiently expand the size of positive examples for six emotion categories (happiness, anger, excitement, desperation, boredom and indifference) in EmoTweet-28 by exploiting tweets collected from distant supervision (DS) that are similar to the seed examples in EmoTweet-28 (ET-seed). Similarity scoring approach was used to compute to cosine similarity scores between each DS tweet and all ET-seed tweets under the same emotion category. Seven vector representations (USE, InferSent GloVe, InferSent fastText, Word2Vec, fastText, GloVe, and Bag-of-Words) were experimented to represent the tweets in the similarity scoring approach. DS tweets with high similarity scores were selected to become the augmented instances and annotated with emotion labels. The selection of DS tweets was divided into two categories which are threshold-based selection and fixed increment selection. In addition, we also modified the proposed text augmentation strategy by altering the seed sets used for similarity scoring using clustering and misclassified strategies. All augmented sets were evaluated by training a deep neural network classifier separately to distinguish between the presence or absence of specific emotion in tweets from the test set.
first_indexed 2025-11-15T19:01:10Z
format Thesis
id usm-59117
institution Universiti Sains Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T19:01:10Z
publishDate 2022
recordtype eprints
repository_type Digital Repository
spelling usm-591172023-08-14T06:38:11Z http://eprints.usm.my/59117/ Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models Yong, Kuan Shyang QA76.6 Electronic digital computers -- Programming Emotion classification can benefit from a larger pool of training data but manually expanding the emotion corpus is labour-intensive and time-consuming. Distant supervision can be used to collect large amount of training data in a short period of time using emotion word hashtags, but the collected data may contain excessive noise. In this research, we proposed a text augmentation strategy to efficiently expand the size of positive examples for six emotion categories (happiness, anger, excitement, desperation, boredom and indifference) in EmoTweet-28 by exploiting tweets collected from distant supervision (DS) that are similar to the seed examples in EmoTweet-28 (ET-seed). Similarity scoring approach was used to compute to cosine similarity scores between each DS tweet and all ET-seed tweets under the same emotion category. Seven vector representations (USE, InferSent GloVe, InferSent fastText, Word2Vec, fastText, GloVe, and Bag-of-Words) were experimented to represent the tweets in the similarity scoring approach. DS tweets with high similarity scores were selected to become the augmented instances and annotated with emotion labels. The selection of DS tweets was divided into two categories which are threshold-based selection and fixed increment selection. In addition, we also modified the proposed text augmentation strategy by altering the seed sets used for similarity scoring using clustering and misclassified strategies. All augmented sets were evaluated by training a deep neural network classifier separately to distinguish between the presence or absence of specific emotion in tweets from the test set. 2022-08 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/59117/1/YONG%20KUAN%20SHYANG%20-%20TESIS.pdf Yong, Kuan Shyang (2022) Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models. Masters thesis, Universiti Sains Malaysia.
spellingShingle QA76.6 Electronic digital computers -- Programming
Yong, Kuan Shyang
Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title_full Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title_fullStr Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title_full_unstemmed Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title_short Text Augmentation For Emotion Classification In Microblog Text Using Similarity Scoring Based On Neural Embedding Models
title_sort text augmentation for emotion classification in microblog text using similarity scoring based on neural embedding models
topic QA76.6 Electronic digital computers -- Programming
url http://eprints.usm.my/59117/
http://eprints.usm.my/59117/1/YONG%20KUAN%20SHYANG%20-%20TESIS.pdf