Reasoning in Natural Language: Assessing Large Language Model capabilities in Sentiment Analysis
A report dedicated to the most current research aimed at using Large Language Models (LLMs) in the field of Sentiment Analysis. This task involves extracting the author’s opinion from the text to the entity mentioned in the text.
You will learn:
(1) how well LLMs reasoning can be used for reasoning in sentiment analysis as in Zero-shot-Learning,
(2) how to improve reasoning by applying and leaving step-by-step chains (Chain-of- Thought),
(3) how to prepare the most advanced model in sentiment analysis using Chain-of-Thought.
The report is expected to provide results and conclusions based on experiments on the RuSentNE-2023 corpus for open models and proprietary (ChatGPT) for reasoning in the field of sentiment analysis on English and non-English texts
Nicolay Rusnachenko
Research Fellow at Bournemouth University
Information Retrieval Researcher. Majored in Multimodal (image+text) and Textual Natural Language Processing (NLP) from mass-media articles, news, literature books, medical texts. Contributed in advances of large document processing in such fields as: Sentiment Analysis, Text Summarization. At present he is doing studies in medical domain by developing multimodal assistant and contribute to NHS advances.
