Technology Category
Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP ModelsData Mining & Knowledge Management: Recommender SystemsKnowledge Representation and Reasoning: Preferences
Are some books better than others?
🤖 AI Summary
This study investigates the relative contributions of objective book attributes versus subjective reader characteristics in book reviews. Method: Leveraging 624,000 numerical ratings and associated textual reviews, we employ large-scale text statistics, mutual information estimation, cross-rater consistency modeling, topic coherence assessment, and regression analysis. Contribution/Results: We provide the first empirical evidence that review content predominantly encodes reviewer-specific traits—not intrinsic book properties. Published content exhibits negligible predictive power for individual reader experience. In popular books, reviewer-related information exceeds book-related information by an order of magnitude (10×). Inter-review consistency on evaluative dimensions is extremely low, indicating poor predictive transfer across reviews of the same book. Moreover, professional reviewers demonstrate significantly higher cross-rater generalizability than non-experts. These findings substantiate epistemic perspectivism in literary evaluation and offer theoretical grounding and empirical validation for its integration into recommendation system design.
Technology Category
Application Category
📝 Abstract
Scholars, awards committees, and laypeople frequently discuss the merit of written works. Literary professionals and journalists differ in how much perspectivism they concede in their book reviews. Here, we quantify how strongly book reviews are determined by the actual book contents vs. idiosyncratic reader tendencies. In our analysis of 624,320 numerical and textual book reviews, we find that the contents of professionally published books are not predictive of a random reader's reading enjoyment. Online reviews of popular fiction and non-fiction books carry up to ten times more information about the reviewer than about the book. For books of a preferred genre, readers might be less likely to give low ratings, but still struggle to converge in their relative assessments. We find that book evaluations generalize more across experienced review writers than casual readers. When discussing specific issues with a book, one review text had poor predictability of issues brought up in another review of the same book. We conclude that extreme perspectivism is a justifiable position when researching literary quality, bestowing literary awards, and designing recommendation systems.
Problem
Research questions and friction points this paper is trying to address.
Quantify influence of book content vs. reader tendencies in reviews.
Assess predictability of reader enjoyment from book content.
Evaluate consistency and generalization of book reviews across readers.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Quantified book review determinants
Analyzed 624,320 book reviews
Assessed reviewer vs. book information
🔎 Similar Papers
No similar papers found.
