REVIEW 5 cited by
Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recently, ChatGPT has drawn great attention from both the research community and the public. We are particularly interested in whether it can serve as a universal sentiment analyzer. To this end, in this work, we provide a preliminary evaluation of ChatGPT on the understanding of \emph{opinions}, \emph{sentiments}, and \emph{emotions} contained in the text. Specifically, we evaluate it in three settings, including \emph{standard} evaluation, \emph{polarity shift} evaluation and \emph{open-domain} evaluation. We conduct an evaluation on 7 representative sentiment analysis tasks covering 17 benchmark datasets and compare ChatGPT with fine-tuned BERT and corresponding state-of-the-art (SOTA) models on them. We also attempt several popular prompting techniques to elicit the ability further. Moreover, we conduct human evaluation and present some qualitative case studies to gain a deep comprehension of its sentiment analysis capabilities.
Forward citations
Cited by 5 Pith papers
-
Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation
The work reframes explainable recommendation as statement-level ranking, introduces the StaR benchmark from Amazon reviews, and finds popularity baselines outperforming SOTA models in item-level personalized ranking.
-
Visibility vs. Engagement: How Two Indian News Websites Reported on LGBTQ+ Individuals and Communities during the Pandemic
Indian news websites gave LGBTQ+ communities visibility during the pandemic but often with little depth, and Times of India's language was at times transphobic.
-
MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction
MEKiT improves LLM emotion-cause pair extraction by adding emotional label knowledge to instruction prompts and mixing causal examples into training data, achieving 61.49 F1 on NTCIR-13.
-
FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis
FCKT improves targeted sentiment analysis through fine-grained transfer of aspect boundary knowledge into sentiment prediction, using token-level contrastive learning and an alternating real/predicted training strategy.
-
Can ChatGPT Perform Image Splicing Detection? A Preliminary Study
GPT-4.1 detects image splicing on a curated CASIA v2.0 subset with over 85% zero-shot accuracy, and chain-of-thought prompting gives the most balanced performance across authentic and spliced images.
Discussion (0). Continue with ORCID to comment.