Optimizing High-Dimensional Text Embeddings in Emotion Identification: A Sliding Window Approach

Hande Aka Uymaz, Senem Kumova Metin

2024

Abstract

Natural language processing (NLP) is an interdisciplinary field that enables machines to understand and generate human language. One of the crucial steps in several NLP tasks, such as emotion and sentiment analysis, text similarity, summarization, and classification, is transforming textual data sources into numerical form, a process called vectorization. This process can be grouped into traditional, semantic, and contextual vectorization methods. Despite their advantages, these high-dimensional vectors pose memory and computational challenges. To address these issues, we employed a sliding window technique to partition high-dimensional vectors, aiming not only to enhance computational efficiency but also to detect emotional information within specific vector dimensions. Our experiments utilized emotion lexicon words and emotionally labeled sentences in both English and Turkish. By systematically analyzing the vectors, we identified consistent patterns with emotional clues. Our findings suggest that focusing on specific sub-vectors rather than entire high-dimensional BERT vectors can capture emotional information effectively, without performance loss. With this approach, we examined an increase in pairwise cosine similarity scores within emotion categories when using only sub-vectors. The results highlight the potential of the use of sub-vector techniques, offering insights into the nuanced integration of emotions in language and the applicability of these methods across different languages.

Paper Citation

in Harvard Style

Aka Uymaz H. and Kumova Metin S. (2024). Optimizing High-Dimensional Text Embeddings in Emotion Identification: A Sliding Window Approach. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-716-0, SciTePress, pages 258-266. DOI: 10.5220/0012899300003838

in Bibtex Style

@conference{kdir24,
author={Hande Aka Uymaz and Senem Kumova Metin},
title={Optimizing High-Dimensional Text Embeddings in Emotion Identification: A Sliding Window Approach},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2024},
pages={258-266},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012899300003838},
isbn={978-989-758-716-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Optimizing High-Dimensional Text Embeddings in Emotion Identification: A Sliding Window Approach
SN - 978-989-758-716-0
AU - Aka Uymaz H.
AU - Kumova Metin S.
PY - 2024
SP - 258
EP - 266
DO - 10.5220/0012899300003838
PB - SciTePress