How Effectively Do LLMs Extract Feature-Sentiment Pairs from App Reviews?

• URL: http://arxiv.org/abs/2409.07162v3
• Date: Sun, 09 Feb 2025 14:12:58 GMT
• Title: How Effectively Do LLMs Extract Feature-Sentiment Pairs from App Reviews?
• Authors: Faiz Ali Shah, Ahmed Sabir, Rajesh Sharma, Dietmar Pfahl,
• Abstract summary: This study compares the performance of state-of-the-art LLMs, including GPT-4, ChatGPT, and different variants of Llama-2 chat. For predicting positive and neutral sentiments, GPT-4 achieves f1-scores of 76% and 45% in the zero-shot setting.
• Score: 2.218667838700643
• License:
• Abstract: Automatic analysis of user reviews to understand user sentiments toward app functionality (i.e. app features) helps align development efforts with user expectations and needs. Recent advances in Large Language Models (LLMs) such as ChatGPT have shown impressive performance on several new tasks without updating the model's parameters i.e. using zero or a few labeled examples, but the capabilities of LLMs are yet unexplored for feature-specific sentiment analysis. The goal of our study is to explore the capabilities of LLMs to perform feature-specific sentiment analysis of user reviews. This study compares the performance of state-of-the-art LLMs, including GPT-4, ChatGPT, and different variants of Llama-2 chat, against previous approaches for extracting app features and associated sentiments in zero-shot, 1-shot, and 5-shot scenarios. The results indicate that GPT-4 outperforms the rule-based SAFE by 17% in f1-score for extracting app features in the zero-shot scenario, with 5-shot further improving it by 6%. However, the fine-tuned RE-BERT exceeds GPT-4 by 6% in f1-score. For predicting positive and neutral sentiments, GPT-4 achieves f1-scores of 76% and 45% in the zero-shot setting, which improve by 7% and 23% in the 5-shot setting, respectively. Our study conducts a thorough evaluation of both proprietary and open-source LLMs to provide an objective assessment of their performance in extracting feature-sentiment pairs.

Related papers

• Language Models are Few-Shot Graders [0.12289361708127876]
  We present an ASAG pipeline leveraging state-of-the-art LLMs. We compare the grading performance of three OpenAI models: GPT-4, GPT-4o, and o1-preview. Our findings indicate that providing graded examples enhances grading accuracy, with RAG-based selection outperforming random selection.
  arXiv  Detail & Related papers  (2025-02-18T23:38:21Z)
• MedSlice: Fine-Tuned Large Language Models for Secure Clinical Note Sectioning [2.4060718165478376]
  Fine-tuned open-source LLMs can surpass proprietary models in clinical note sectioning. This study focuses on three sections: History of Present Illness, Interval History, and Assessment and Plan.
  arXiv  Detail & Related papers  (2025-01-23T21:32:09Z)
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints [86.59857711385833]
  We introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback.
  arXiv  Detail & Related papers  (2024-10-09T01:25:10Z)
• See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses [51.975495361024606]
  We propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses.
  arXiv  Detail & Related papers  (2024-08-16T19:01:52Z)
• GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition? [82.40761196684524]
  This paper centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks. We conduct extensive experiments to evaluate GPT-4's performance across images, videos, and point clouds. Our findings show that GPT-4, enhanced with rich linguistic descriptions, significantly improves zero-shot recognition.
  arXiv  Detail & Related papers  (2023-11-27T11:29:10Z)
• ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction [52.14681890859275]
  E-commerce platforms require structured product data in the form of attribute-value pairs. BERT-based extraction methods require large amounts of task-specific training data. This paper explores using large language models (LLMs) as a more training-data efficient and robust alternative.
  arXiv  Detail & Related papers  (2023-10-19T07:39:00Z)
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models [66.12432440863816]
  We propose Prometheus, a fully open-source Large Language Model (LLM) that is on par with GPT-4's evaluation capabilities. Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics. Prometheus achieves the highest accuracy on two human preference benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:50:08Z)
• Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance [11.595274304409937]
  Large language models (LLMs) have revolutionized zero-shot task performance. Current methods using trigger phrases such as "Let's think step by step" remain limited. This study introduces PRomPTed, an approach that optimize the zero-shot prompts for individual task instances.
  arXiv  Detail & Related papers  (2023-10-03T14:51:34Z)
• Split and Merge: Aligning Position Biases in LLM-based Evaluators [22.265542509143756]
  PORTIA is an alignment-based system designed to mimic human comparison strategies to calibrate position bias. Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested. It rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%.
  arXiv  Detail & Related papers  (2023-09-29T14:38:58Z)
• Exploring Small Language Models with Prompt-Learning Paradigm for Efficient Domain-Specific Text Classification [2.410463233396231]
  Small language models (SLMs) offer significant customizability, adaptability, and cost-effectiveness for domain-specific tasks. In few-shot settings when prompt-based model fine-tuning is possible, T5-base, a typical SLM with 220M parameters, achieve approximately 75% accuracy with limited labeled data. In zero-shot settings with a fixed model, we underscore a pivotal observation that, although the GPT-3.5-turbo equipped with around 154B parameters garners an accuracy of 55.16%, the power of well designed prompts becomes evident.
  arXiv  Detail & Related papers  (2023-09-26T09:24:46Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.