This study introduces novel methods for sentiment and opinion classification of tweets to support the New Product Development (NPD) process. Two popular word embedding techniques, Word2Vec and BERT, were evaluated as inputs for classic Machine Learning and Deep Learning algorithms to identify the best-performing approach in sentiment analysis and opinion detection with limited data. The results revealed that BERT word embeddings combined with Balanced Random Forest yielded the most accurate single model for both sentiment analysis and opinion detection on a use case. Additionally, the paper provides feedback for future product development performing word graph analysis of the tweets with same sentiment to highlight potential areas of improvement.

翻译：本研究提出了通过情感与观点分类推文以支持新产品开发(NPD)流程的新方法。为在数据有限的条件下识别情感分析与观点检测的最佳方法，论文评估了Word2Vec与BERT两种主流词嵌入技术作为经典机器学习和深度学习算法输入的性能。结果表明，在特定用例的情感分析与观点检测任务中，BERT词嵌入结合平衡随机森林模型取得了最高的单模型准确率。此外，论文通过对具有相同情感的推文进行词图分析，为未来产品开发提供了反馈，以突出潜在的改进方向。