Electric Vehicle Sentiment Analysis Using Large Language Models

Опубликована: Авг. 9, 2024

Sentiment analysis is a technique used to understand the publics’ opinion towards an event, product, or organization. For example, positive negative attitude electric vehicle (EV) brands. This provides companies with valuable insight about public's of their products and In field natural language processing (NLP), transformer models have shown great performances over traditional machine learning algorithms. However, these not been explored extensively in EV domain. are becoming signif-icant competitors automotive industry projected cover up 30% United States light market by 2030 [1]. this study, we present comparative study large (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimized BERT approach generalized autoregressive pretraining for un-derstanding using Lucid motors Tesla YouTube datasets. Results evidenced LLMs like her variants off-the-shelf algorithms sentiment analysis, specifically, when fi-ne-tuned. Furthermore, our findings presents need domain adaptation whilst utilizing LLMs. Finally, experimental results showed that RoBERTa achieved consistent performance across datasets F1 score at least 92%.

Язык: Английский

---

Electric Vehicle Sentiment Analysis Using Large Language Models

Analytics, Год журнала: 2024, Номер 3(4), С. 425 - 438

Опубликована: Ноя. 1, 2024

Sentiment analysis is a technique used to understand the public’s opinion towards an event, product, or organization. For example, sentiment can be positive negative opinions attitudes electric vehicle (EV) brands. This provides companies with valuable insight into of their products and In field natural language processing (NLP), transformer models have shown great performance compared traditional machine learning algorithms. However, these not been explored extensively in EV domain. are becoming significant competitors automotive industry projected cover up 30% United States light market by 2030 this study, we present comparative study large (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimised BERT (RoBERTa), generalised autoregressive pre-training method (XLNet) using Lucid Motors Tesla YouTube datasets. Results evidenced that LLMs like her variants off-the-shelf algorithms for analysis, specifically when fine-tuned. Furthermore, our findings need domain adaptation whilst utilizing LLMs. Finally, experimental results showed RoBERTa achieved consistent across datasets F1 score at least 92%.

Язык: Английский

---

An Integrative Framework for Healthcare Recommendation Systems: Leveraging the Linear Discriminant Wolf–Convolutional Neural Network (LDW-CNN) Model

Diagnostics, Год журнала: 2024, Номер 14(22), С. 2511 - 2511

Опубликована: Ноя. 9, 2024

In the evolving healthcare landscape, recommender systems have gained significant importance due to their role in predicting and anticipating a wide range of health-related data for both patients professionals. These are crucial delivering precise information while adhering high standards quality, reliability, authentication.

Язык: Английский

---

GRUvader: Sentiment-Informed Stock Market Prediction

Mathematics, Год журнала: 2024, Номер 12(23), С. 3801 - 3801

Опубликована: Ноя. 30, 2024

Stock price prediction is challenging due to global economic instability, high volatility, and the complexity of financial markets. Hence, this study compared several machine learning algorithms for stock market further examined influence a sentiment analysis indicator on prices. Our results were two-fold. Firstly, we used lexicon-based approach identify features, thus evidencing correlation between movement. Secondly, proposed use GRUvader, an optimal gated recurrent unit network, prediction. findings suggest that stand-alone models struggled with AI-enhanced models. Thus, our paper makes recommendations latter systems.

Язык: Английский

---