Sentiment analysis is a natural language processing task that aims to identify and extract the emotional aspects of a text. However, many existing sentiment analysis methods primarily classify the overall polarity of a text, overlooking the specific phrases that convey sentiment. In this paper, we applied an approach to sentiment analysis based on a question-answering framework. Our approach leverages the power of Bidirectional Autoregressive Transformer (BART), a pre-trained sequence-to-sequence model, to extract a phrase from a given text that amplifies a given sentiment polarity. We create a natural language question that identifies the specific emotion to extract and then guide BART to pay attention to the relevant emotional cues in the text. We use a classifier within BART to predict the start and end positions of the answer span within the text, which helps to identify the precise boundaries of the extracted emotion phrase. Our approach offers several advantages over most sentiment analysis studies, including capturing the complete context and meaning of the text and extracting precise token spans that highlight the intended sentiment. We achieved an end loss of 87% and Jaccard score of 0.61.

翻译：情感分析是一种自然语言处理任务，旨在识别和提取文本中的情感特征。然而，许多现有情感分析方法主要对文本的整体极性进行分类，忽略了传递情感的具体短语。本文基于问答框架提出了一种情感分析方法。该方法利用双向自回归Transformer（BART）这一预训练的序列到序列模型，从给定文本中提取能够放大特定情感极性的短语。我们构建了一个识别待提取具体情绪的自然语言问题，并引导BART关注文本中相关的情感线索。通过BART内部的分类器预测答案跨度在文本中的起始和结束位置，从而精准确定所提取情感短语的边界。与大多数情感分析研究相比，我们的方法具有若干优势，包括捕获文本的完整上下文与含义，以及提取突出目标情感的精确标记跨度。实验最终损失为87%，Jaccard系数为0.61。