Text-Based Emotion Recognition Using Deep Learning Approach

Bharti, Santosh Kumar; Varadhaganapathy, S; Gupta, R. K.; Shukla, Prashant Kumar; Bouye, Mohamed; Hinga, Simon Karanja; Mahmoud, Amena

doi:10.1155/2022/2645381

Cited by 49 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the initial phase, this study adhered to conventional practices in unstructured text learning by executing TF-IDF for training ML models and a word embedding model for DL models. It has been stated that text vectorization, such as TF-IDF performs better in ML models ( Bharti et al, 2022 ), whereas the word-embedding model, for example GloVe works well in DL models ( Kilimci & Akyokus, 2018 ). This standard approach served as the baseline for the text representation experiment.…”

Section: Methodsmentioning

confidence: 99%

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Khairuddin,

Sankaranarayanan,

Hasikin

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Background This study introduced a novel approach for predicting occupational injury severity by leveraging deep learning-based text classification techniques to analyze unstructured narratives. Unlike conventional methods that rely on structured data, our approach recognizes the richness of information within injury narrative descriptions with the aim of extracting valuable insights for improved occupational injury severity assessment. Methods Natural language processing (NLP) techniques were harnessed to preprocess the occupational injury narratives obtained from the US Occupational Safety and Health Administration (OSHA) from January 2015 to June 2023. The methodology involved meticulous preprocessing of textual narratives to standardize text and eliminate noise, followed by the innovative integration of Term Frequency-Inverse Document Frequency (TF-IDF) and Global Vector (GloVe) word embeddings for effective text representation. The proposed predictive model adopts a novel Bidirectional Long Short-Term Memory (Bi-LSTM) architecture and is further refined through model optimization, including random search hyperparameters and in-depth feature importance analysis. The optimized Bi-LSTM model has been compared and validated against other machine learning classifiers which are naïve Bayes, support vector machine, random forest, decision trees, and K-nearest neighbor. Results The proposed optimized Bi-LSTM models’ superior predictability, boasted an accuracy of 0.95 for hospitalization and 0.98 for amputation cases with faster model processing times. Interestingly, the feature importance analysis revealed predictive keywords related to the causal factors of occupational injuries thereby providing valuable insights to enhance model interpretability. Conclusion Our proposed optimized Bi-LSTM model offers safety and health practitioners an effective tool to empower workplace safety proactive measures, thereby contributing to business productivity and sustainability. This study lays the foundation for further exploration of predictive analytics in the occupational safety and health domain.

show abstract

Section: Methodsmentioning

confidence: 99%

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Khairuddin,

Sankaranarayanan,

Hasikin

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In that they classify emotions differently, machine learning and deep learning methodologies are distinct. (Bharti, 2022) Cognitive science is an interdisciplinary eld of study that examines various cognitive processes and sophisticated human behaviors, including perception, thinking, remembering, learning, reasoning, and emotions. Emotions are among the most essential faculties for identifying human social behaviors.…”

Section: Literature Reviewmentioning

confidence: 99%

Impact of tweets on Indian movies performance: An integrative approach using sentiment analysis and emotion detection

Sarin,

Agarwal,

Goyal

2023

Preprint

View full text Add to dashboard Cite

Due to social media's rapid growth, moviegoers primarily rely on internet reviews before buying. Studios must determine how reviews affect sales. This study examines how online reviews affect movie box office earnings using sentiment analysis and emotion recognition. Text reviews affect attendance and revenue as much as rating does. This data can help filmmakers and advertising target demographics. Films met audience expectations, with increased trust and happiness and lower wrath, surprise, disgust, and sadness. However, some films scored better for specific emotions, suggesting they elicited different audience responses. Most film tweets were happier and more trusting after release than before. However, tweets about some films showed more wrath and dread, suggesting marketing or audience reception concerns.

show abstract

“…It determines subjects, each of which is the probability distribution over phrases [16][17][18] . At this point, all of these subjects are calculated by applying a hierarchical Bayesian process, in which every sentence in the document can be represented as a combined collection of a number comprising various subjects [19,20] . As a result of its ability to successfully analyze a significant quantity of unlabeled textual data, this model is a highly beneficial tool for ML [21][22][23][24][25] .…”

Section: Introductionmentioning

confidence: 99%

Relationship between mental health and job competence of college teachers: Application of sentiment analysis algorithm

Wu,

Zhuo

2024

Environ. Soc. Psychol.

View full text Add to dashboard Cite

In systematically collecting and investigating data related to the teaching field, the association between teachers’ Mental Health (MH) and Job Competence (JC) is an important field that has not been systematically studied. Understanding this association is vital due to its direct impact on the Quality of Education (QoE) and its standard educational system. Due to problems in evaluating all qualitative data, such as Open-Ended Survey Feedback (OESF), traditional models frequently find it challenging to epitomize intricate relations accurately. This article reports on these tasks by introducing a Mixed-Method Approach (MMA). The research study was directed through online learning across numerous higher education institutions in three provinces of China, and a combination analysis of quantitative study data using qualitative Sentiment Analysis (SA) was recommended. The new thing about the method is that it suggests an algorithm based on Latent Dirichlet Allocation (LDA) to SA that lets all of the qualitative data from the OESF questions be studied. This algorithm suggests a more philosophical knowledge of teachers’ MH and its association with their specialized skills overall OESF. The study’s results represent a significant insight into the dynamics between MH and JC related to College Teachers (CT). It highlights how every feature impacts others and the prerequisites for educational strategies supporting teacher well-being. By overcoming boundaries in existing models, the proposed work contributes to a broader and better knowledge of teacher well-being, its impact on educational quality, and the potential for SA in educational research. We compared how well three classifiers—Naïve Bayes (NB), Support Vector Machine (SVM), and Linear Regression (LR)—performed on six topics that were chosen for this SA research. The performance analysis for evaluation is accuracy, precision, recall, and F1-score. The reliability of the OESF measures was confirmed with Cronbach’s alpha values signifying high internal consistency: 0.85 for JC, 0.88 for MH status, and 0.82 for innovative teaching ability.

show abstract

Text-Based Emotion Recognition Using Deep Learning Approach

Cited by 49 publications

References 32 publications

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Impact of tweets on Indian movies performance: An integrative approach using sentiment analysis and emotion detection

Relationship between mental health and job competence of college teachers: Application of sentiment analysis algorithm

Contact Info

Product

Resources

About