Sentiment and Context-refined Word Embeddings for Sentiment Analysis

Date

2021-01-01

Author

Deniz, Ayca
Angin, Merih
Angın, Pelin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

73
views

0
downloads

Word embeddings have become the de-facto tool for representing text in natural language processing (NLP) tasks, as they can capture semantic and syntactic relations, unlike their precedents such as Bag-of-Words. Although word embeddings have been employed in various studies in recent years and proven to be effective in many NLP tasks, they are still immature for sentiment analysis, as they suffer from insufficient sentiment information. General word embedding models pre-trained on large corpora with methods such as Word2Vec or GloVe achieve limited success in domain-specific NLP tasks. On the other hand, training domain-specific word embeddings from scratch requires a high amount of data and computation power. In this work, we target both shortcomings of pre-trained word embeddings to boost the performance of domain-specific sentiment analysis tasks. We propose a model that refines pre-trained word embeddings with context information and leverages the sentiment scores of sentences obtained from a lexicon-based method to further improve performance. Experiment results on two benchmark datasets show that the proposed method significantly increases the accuracy of sentiment classification.

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85124303320&origin=inward
https://hdl.handle.net/11511/96968

DOI

https://doi.org/10.1109/smc52423.2021.9659189

Conference Name

2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Semantic dimensionality reduction during language acquisition: A window into concept representation Özcan, Rojda; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2022-8-31) We explore the dimensionality in the semantic representations derived from the Eve fragment of the CHILDES database to gain insights into whether or not semantic dimensionality reduc- tion (DR) occurs during language acquisition, and if so to gain insights into how this reduction of dimensions could look like. We start exploring these representations that are in the form of lambda terms (LTs) by trying to find different representations for them which would be more suitable for the use of DR techniques on th...
Data interoperability through federated semantic metadata registries Sınacı, Ali Anıl; Çiçekli, Fehime Nihan; Doğaç, Asuman; Department of Computer Engineering (2014) In this study, a unified methodology together with the supporting framework for the problem of data interoperability is introduced which brings together the power of metadata registries and semantic web technologies. A federated architecture of semantic metadata registries which are purely based on ISO/IEC 11179 standard leads to the Linked Open Data integration of data element repositories where each element can be uniquely identified, referenced and processed to enable the syntactic and semantic interoper...
Object Detection with Convolutional Context Features Kaya, Emre Can; Alatan, Abdullah Aydın (2017-01-01) A novel extension to Huh B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two parallel networks. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection ben...
Conditional Random Fields for Land Use/Land Cover Classification and Complex Region Detection Can, Gulcan; Firat, Orhan; Yarman Vural, Fatoş Tunay (2012-11-09) Developing a complex region detection algorithm that is aware of its contextual relations with several classes necessitates statistical frameworks that can encode contextual relations rather than simple rule-based applications or heuristics. In this study, we present a conditional random field (CRF) model that is generated over the results of a robust local discriminative classifier in order to reveal contextual relations of complex objects and land use/land cover (LULC) classes. The proposed CRF model enco...
Diacritics correction in Turkish with context-aware sequence to sequence modeling Köksal, Asiye Tuba; Bozal, Özge; Özge, Umut (2022-1-01) Digital texts in many languages have examples of missing or misused diacritics which makes it hard for natural language processing applications to disambiguate the meaning of words. Therefore, diacritics restoration is a crucial step in natural language processing applications for many languages. In this study we approach this problem as bidirectional transformation of diacritical letters and their ASCII counterparts, rather than unidirectional diacritic restoration. We propose a context-aware character-lev...

Citation Formats

A. Deniz, M. Angin, and P. Angın, “Sentiment and Context-refined Word Embeddings for Sentiment Analysis,” presented at the 2021 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2021, Melbourne, Avustralya, 2021, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85124303320&origin=inward.