Vector based sentiment and emotion analysis from text: A survey

Uymaz, Hande Aka; Metin, Senem Kumova

doi:10.1016/j.engappai.2022.104922

Cited by 18 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using word embedding [7] to represent fraudulent phone text, its semantic information can be accurately expressed. Word2Vec [8], and Glove [9] are representative word embeddings in text classification tasks. Word2Vec is a distributed representation method.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Zhou¹,

Xu²,

Zhang³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Fraud cases have been a risk in society and people's property security has been greatly threatened. In recent studies, many promising algorithms have been developed for social media offensive text recognition as well as sentiment analysis. These algorithms are also suitable for fraudulent phone text recognition. Compared to these tasks, the semantics of fraudulent words are more complex and more difficult to distinguish. Recurrent Neural Networks (RNN), the variants of RNN, Convolutional Neural Networks (CNN), and hybrid neural networks to extract text features are used by most text classification research. However, a single network or a simple network combination cannot obtain rich characteristic knowledge of fraudulent phone texts relatively. Therefore, a new model is proposed in this paper. In the fraudulent phone text, the knowledge that can be learned by the model includes the sequence structure of sentences, the correlation between words, the correlation of contextual semantics, the feature of keywords in sentences, etc. The new model combines a bidirectional Long-Short Term Memory Neural Network (BiLSTM) or a bidirectional Gate Recurrent United (BiGRU) and a Multi-Head attention mechanism module with convolution. A normalization layer is added after the output of the final hidden layer. BiLSTM or BiGRU is used to build the encoding and decoding layer. Multi-head attention mechanism module with convolution (MHAC) enhances the ability of the model to learn global interaction information and multi-granularity local interaction information in fraudulent sentences. A fraudulent phone text dataset is produced by us in this paper. The THUCNews data sets and fraudulent phone text data sets are used in experiments. Experiment results show that compared with the baseline model, the proposed model (LMHACL) has the best experiment results in terms of Accuracy, Precision, Recall, and F1 score on the two data sets. And the performance indexes on fraudulent phone text data sets are all above 0.94.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Multiple sets of W Q , W K , and W V matrices are initialized, and the global interaction information at different angles can be obtained. The global interaction of each angle is combined to form the global interaction of the multi-head attention mechanism, as shown in the formula (8).…”

Section: Multi-head Attention Mechanismmentioning

confidence: 99%

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Zhou¹,

Xu²,

Zhang³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Sentiment analysis studies have recently expanded to include multimodal and cross-lingual analysis, moving beyond traditional text-based methods. These advanced approaches leverage machine learning to analyze emotions conveyed through various multimedia forms, such as audio, video, and images [14]. This evolution from rule-based and machinelearning-based approaches to deep learning techniques has significantly improved sentiment analysis accuracy and efficiency, benefiting industries like healthcare, advertising, and entertainment [15].…”

Section: Literature Reviewmentioning

confidence: 99%

Multimodal Deep Learning Approach for Real-Time Sentiment Analysis in Video Streaming

2023

IJACSA

View full text Add to dashboard Cite

Recognizing emotions from visual data, like images and videos, presents a daunting challenge due to the intricacy of visual information and the subjective nature of human emotions. Over the years, deep learning has showcased remarkable success in diverse computer vision tasks, including sentiment classification. This paper introduces a novel multi-view deep learning framework for emotion recognition from visual data. Leveraging Convolutional Neural Networks (CNNs) this framework extracts features from visual data to enhance sentiment classification accuracy. Additionally, we enhance the deep learning model through cutting-edge techniques like transfer learning to bolster its generalization capabilities. Furthermore, we develop an efficient deep learning classification algorithm, effectively categorizing visual sentiments based on the extracted features. To assess its performance, we compare our proposed model with state-of-the-art machine learning methods in terms of classification accuracy, training time, and processing speed. The experimental results unequivocally demonstrate the superiority of our framework, showcasing higher classification accuracy, faster training times, and improved processing speed compared to existing methods. This multi-view deep learning approach marks a significant stride in emotion recognition from visual data and holds the potential for various real-world applications, such as social media sentiment analysis and automated video content analysis.

show abstract

“…Therefore, a model representation enriched with emotion and sentiment is needed. The enhanced methods can be concentrated into four categories: keyword-based, lexicon-based, learning-based, and hybrid [6].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Method on Emotion Detection for Indonesian Tweets of COVID-19

Purwitasari¹,

Ansyah²,

Kurniawan³

et al. 2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

As a result of the COVID-19 pandemic, there have been restrictions on activities outside the home which has caused people to interact more and express their emotions through social media platforms, one of which is Twitter. Previous studies on emotion classification used only one feature extraction, namely the lexicon based or word embedding. Feature extraction using the emotion lexicon has the advantage of recognizing emotional words in a sentence while feature extraction using word embedding has the advantage of recognizing the semantic meaning. Therefore, the main contribution to this research is to use two lexicon feature extraction and word embedding to classify emotions. The classification technique used in this research is the Ensemble Voting Classifier by selecting the two best classifiers to try on both types of feature extraction. The experimental results for both types of feature extraction are the same, indicating that the best classifiers are Random Forest and SVM. Models using both types of feature extraction show increased accuracy compared to using only one feature extraction. The results of this emotional analysis can be used to determine the public's reaction to an event, product, or public policy.

show abstract

Vector based sentiment and emotion analysis from text: A survey

Cited by 18 publications

References 51 publications

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Using Recurrent Neural Network Structure and Multi-Head Attention with Convolution for Fraudulent Phone Text Recognition

Multimodal Deep Learning Approach for Real-Time Sentiment Analysis in Video Streaming

A Hybrid Method on Emotion Detection for Indonesian Tweets of COVID-19

Contact Info

Product

Resources

About