# Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models

arXiv: https://arxiv.org/abs/2509.02363 · HTML: https://mlsanity.com/paper/2509.02363/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster](https://mlsanity.com/paper/2503.07649/) (2025)
- [Aspect Term Extraction with History Attention and Selective Transformation](https://mlsanity.com/paper/1805.00760/) (2018)
- [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021)
- [A Multi-task Learning Framework for Opinion Triplet Extraction](https://mlsanity.com/paper/2010.01512/) (2020)
- [Are Large Language Models Reliable Argument Quality Annotators?](https://mlsanity.com/paper/2404.09696/) (2024)
- [Assessing Consistency and Reproducibility in the Outputs of Large Language Models: Evidence Across Diverse Finance and Accounting Tasks](https://mlsanity.com/paper/2503.16974/) (2025)
- [Detecting Topic and Sentiment Dynamics Due to COVID-19 Pandemic Using Social Media](https://mlsanity.com/paper/2007.02304/) (2020)
- [StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series](https://mlsanity.com/paper/2301.09279/) (2023)
- [Subjective Databases](https://mlsanity.com/paper/1902.09661/) (2019)
- [LLMs as Span Annotators: A Comparative Study of LLMs and Humans](https://mlsanity.com/paper/2504.08697/) (2025)
- [If you've got it, flaunt it: Making the most of fine-grained sentiment annotations](https://mlsanity.com/paper/2102.00299/) (2021)
- [Towards Semantic Integration of Opinions: Unified Opinion Concepts Ontology and Extraction Task](https://mlsanity.com/paper/2505.18703/) (2025)

## Built on by (most cited first, 1 of 1)

- [Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach](https://mlsanity.com/paper/2605.03092/) (2026)

## Abstract (arXiv)

We propose a scalable method for constructing a temporal opinion knowledge base with large language models (LLMs) as automated annotators. Despite the demonstrated utility of time-series opinion analysis of text for downstream applications such as forecasting and trend analysis, existing methodologies underexploit this potential due to the absence of temporally grounded fine-grained annotations. Our approach addresses this gap by integrating well-established opinion mining formulations into a declarative LLM annotation pipeline, enabling structured opinion extraction without manual prompt engineering. We define three data models grounded in sentiment and opinion mining literature, serving as schemas for structured representation. We perform rigorous quantitative evaluation of our pipeline using human-annotated test samples. We carry out the final annotations using two separate LLMs, and inter-annotator agreement is computed label-wise across the fine-grained opinion dimensions, analogous to human annotation protocols. The resulting knowledge base encapsulates time-aligned, structured opinions and is compatible with applications in Retrieval-Augmented Generation (RAG), temporal question answering, and timeline summarisation.