MBiLSTMGloVe: Embedding GloVe knowledge into the corpus using multi-layer BiLSTM deep learning model for social media sentiment analysis

Pimpalkar, Amit; Raj, Jeberson Retna

doi:10.1016/j.eswa.2022.117581

Cited by 47 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, word embedding approaches, such as Word2Vec, FastText, and GloVe, encode words as dense vectors in high-dimensional spaces. These techniques capture the semantic and syntactic meaning of words (Pimpalkar, 2022 ; Aoumeur et al, 2023 ; Umer et al, 2023 ), making them effective in sentiment analysis, especially for handling idiomatic expressions, sarcasm, and figurative language. Word2Vec, for instance, trains a neural network on a large text corpus to generate word vectors, enabling accurate word similarity calculations and the improvement of sentiment analysis models.…”

Section: Methodsmentioning

confidence: 99%

Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques

Elmitwalli,

Mehegan

2024

Front. Big Data

View full text Add to dashboard Cite

IntroductionSentiment analysis has become a crucial area of research in natural language processing in recent years. The study aims to compare the performance of various sentiment analysis techniques, including lexicon-based, machine learning, Bi-LSTM, BERT, and GPT-3 approaches, using two commonly used datasets, IMDB reviews and Sentiment140. The objective is to identify the best-performing technique for an exemplar dataset, tweets associated with the WHO Framework Convention on Tobacco Control Ninth Conference of the Parties in 2021 (COP9).MethodsA two-stage evaluation was conducted. In the first stage, various techniques were compared on standard sentiment analysis datasets using standard evaluation metrics such as accuracy, F1-score, and precision. In the second stage, the best-performing techniques from the first stage were applied to partially annotated COP9 conference-related tweets.ResultsIn the first stage, BERT achieved the highest F1-scores (0.9380 for IMDB and 0.8114 for Sentiment 140), followed by GPT-3 (0.9119 and 0.7913) and Bi-LSTM (0.8971 and 0.7778). In the second stage, GPT-3 performed the best for sentiment analysis on partially annotated COP9 conference-related tweets, with an F1-score of 0.8812.DiscussionThe study demonstrates the effectiveness of pre-trained models like BERT and GPT-3 for sentiment analysis tasks, outperforming traditional techniques on standard datasets. Moreover, the better performance of GPT-3 on the partially annotated COP9 tweets highlights its ability to generalize well to domain-specific data with limited annotations. This provides researchers and practitioners with a viable option of using pre-trained models for sentiment analysis in scenarios with limited or no annotated data across different domains.

show abstract

Section: Methodsmentioning

confidence: 99%

Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques

Elmitwalli,

Mehegan

2024

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…By grouping words into several communities, each of which represents a unique idea, community recognition algorithms can automatically extract ideas from text. Biometric surveillance systems that utilize GloVe integration with the BiLSTM framework considerably outperform those that do not, according to research by Pimpalkar and Raj [49]. The importance of word embedding is shown in Table 1, which presents a thorough examination of its performance evaluation, data origin, datasets, and areas of application.…”

Section: Content-based Image Retrievalmentioning

confidence: 99%

Object Recognition to Content Based Image Retrieval: A Study of the Developments and Applications of Computer Vision

Mangalika

2024

JCNS

View full text Add to dashboard Cite

Natural Language Processing (NLP) and Computer Vision (CV) are interconnected fields within the domain of Artificial Intelligence (AI). CV is tasked with the process of engaging with computer systems to effectively interpret and recognize visual data, while NLP is responsible for comprehending and processing the human voice. The two fields have practical applicability in various tasks such as image description generation, object recognition, and question-based answering after a visual input. Deep learning algorithms such as word input are typically employed in enhancing the performance of Content-Based Image Processing (CBIR) techniques. Generally, NLP and CV play a vital role in enhancing computer comprehension and engagements with both visual and written information. This paper seeks to review various major elements of computer vision, such as CBIR, visual effects, image documentation, video documentation, visual learning, and inquiry to explore various databases, techniques, and methods employed in this field. The authors focus on the challenges and progress in each area and offer new strategies for improving the performance of CV systems.

show abstract

“…Lately, researchers have started to modify NN architecture in order to increase classification performance. For instance, [32] utilized a Glove embedding vector with multi-layers of BiLSTM. This model resulted in a 3% improvement in performance when compared with previous research studies.…”

Section: A Machine-learning and Deep-learning Techniques In Sentiment...mentioning

confidence: 99%

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Thiengburanathum,

Charoenkwan

2023

IEEE Access

View full text Add to dashboard Cite

Sentiment classification of social media posts is among the most challenging and timeconsuming tasks for analysts. This is particularly true when applied to languages that employ scriptio continua, such as the Thai language, in which there are no spaces between written words and where there is no end of sentence punctuation. Thai is considered a scarce-resource language as few datasets are available to researchers. Although machine-learning (ML) and deep-learning (DL) algorithms can identify sentiment classification polarity, the performance of the existing classification models are still inadequate. This study proposes a novel stacking ensemble learning technique for identifying sentiment classification polarity in the Thai language, SETAR. Our stacking ensemble strategy utilized the pre-trained Thai language model (WangChanBERTa), based on a Robustly Optimized BERT Pretraining Approach (RoBERTa) architecture to form a feature vector. This feature was combined with three distinct feature vectors obtained from three well-known categories, namely Word2Vec, TF-IDF, and bag-of-words, as a new hybrid sentence representation. The base learners were trained using seven chosen complex heterogeneous ML algorithms, including support vector machine (SVM), random forest (RF), extremely randomized trees (ET), light gradient boosting machine (LGBM), multi-layer perceptron (MLP), partial least squares (PLS), and logistic regression (LR) to enable the development of the final meta-learners. The results revealed that our proposed stacking ensemble model outperformed the baseline models of all classification metrics among the training and test sets, as was determined by extensive benchmarking, carried out on the four datasets, which included our developed sentiment corpus that domain experts annotated.

show abstract

MBiLSTMGloVe: Embedding GloVe knowledge into the corpus using multi-layer BiLSTM deep learning model for social media sentiment analysis

Cited by 47 publications

References 22 publications

Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques

Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques

Object Recognition to Content Based Image Retrieval: A Study of the Developments and Applications of Computer Vision

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Contact Info

Product

Resources

About