This study presents a comprehensive sentiment analysis (SA) of comments on YouTube videos related to Sidewalk Delivery Robots (SDRs). The researchers manually annotated the collected YouTube comments with three sentiment labels: negative (0), positive (1), and neutral (2). They then constructed models for text sentiment classification and tested the models' performance on both binary and ternary classification tasks.
The results indicate that in binary classification tasks, the Support Vector Machine (SVM) model using Term Frequency–Inverse Document Frequency (TF-IDF) and N-gram achieved the highest accuracy. In ternary classification tasks, the model using Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory Networks (LSTM) and Gated Recurrent Unit (GRU) significantly outperformed other machine learning models.
Additionally, the researchers employed the Latent Dirichlet Allocation (LDA) model to generate 10 topics from the comments to explore the public's underlying views on SDRs. The topics revealed a diverse range of public attitudes and concerns, including job security, food delivery applications, prospects of future technology, food and robot safety, and potential conflicts between SDRs and pedestrians.
Based on these findings, the researchers propose targeted recommendations for shaping future policies concerning SDRs, addressing issues such as legal considerations, workforce skill development, traffic control measures, data security, and equitable access to SDR services.
To Another Language
from source content
arxiv.org
Дополнительные вопросы