{"slug": "using-text-based-causal-inference-to-disentangle-factors-influencing-online", "title": "Using Text-Based Causal Inference to Disentangle Factors Influencing Online Review Ratings", "summary": "Researchers introduced a methodology using CausalBERT, enhanced with temperature scaling, hyperparameter optimization, and interpretability methods, to isolate the impact of specific factors on online review ratings. The approach, validated on over 600,000 reviews of U.S. K-12 schools, found that perceptions of school administration and benchmark performance are significant drivers of overall ratings. This work addresses the challenge of disentangling correlated aspects in reviews to better understand their influence on consumer perception.", "body_md": "arXiv:2606.04286v1 Announce Type: new\nAbstract: Online reviews provide valuable insights into the perceived quality of facets of a product or service. While aspect-based sentiment analysis has focused on extracting these facets from reviews, there is less work understanding the impact of each aspect on overall perception. This is particularly challenging given correlations among aspects, making it difficult to isolate the effects of each. This paper introduces a methodology based on recent advances in text-based causal analysis, specifically CausalBERT, to disentangle the effect of each factor on overall review ratings. We enhance CausalBERT with three key improvements: temperature scaling for better calibrated treatment assignment estimates; hyperparameter optimization to reduce confound overadjustment; and interpretability methods to characterize discovered confounds. In this work, we treat the textual mentions in reviews as proxies for real-world attributes. We validate our approach on real and semi-synthetic data from over 600K reviews of U.S. K-12 schools. We find that the proposed enhancements result in more reliable estimates, and that perception of school administration and performance on benchmarks are significant drivers of overall school ratings.", "url": "https://wpnews.pro/news/using-text-based-causal-inference-to-disentangle-factors-influencing-online", "canonical_source": "https://arxiv.org/abs/2606.04286", "published_at": "2026-06-04 04:00:00+00:00", "updated_at": "2026-06-04 04:22:08.194546+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-research"], "entities": ["CausalBERT"], "alternates": {"html": "https://wpnews.pro/news/using-text-based-causal-inference-to-disentangle-factors-influencing-online", "markdown": "https://wpnews.pro/news/using-text-based-causal-inference-to-disentangle-factors-influencing-online.md", "text": "https://wpnews.pro/news/using-text-based-causal-inference-to-disentangle-factors-influencing-online.txt", "jsonld": "https://wpnews.pro/news/using-text-based-causal-inference-to-disentangle-factors-influencing-online.jsonld"}}