Bibliographic record
Abstract
Online consumer reviews have become an important source of information for understanding markets and customer preferences. When making purchase decisions, customers increasingly rely on user-generated online reviews; some even consider the information in online reviews more credible and trustworthy than information provided by vendors. Many studies have revealed that online reviews influence demand and sales. Others have shown the possibility of identifying customer interest in product attributes. However, little work has been done to address customer and review diversity in the process of examining reviews. This research intends to answer the research question: how can we solve the problem of customer and review diversity in the context of online reviews to recommend useful reviews based on customer preferences and improve product recommendation? Our approach to the question is through personalization. Similar to other personalization research, we use an attribute-based model to represent products and customer preferences. Unlike existing personalization research that uses a set of pre-defined product attributes, we explore the possibility of a data-driven approach for identifying more comprehensive product attributes from online reviews to model products and customer preferences. Specifically, we introduce a new topic model for product attribute identification and sentiment analysis. By differentiating word co-occurrences at the sentence level from at the document level, the model better identifies interpretable topics. The use of an inference network with shared structure enables the model to predict product attribute ratings accurately. Based on this topic model, we develop attribute-based representations of products, reviews and customer preferences and use them to construct the personalization of online reviews. We examine personalization from the lens of consumer search theory and human information processing theory and test the hypotheses with an experiment. The personalization of online reviews can 1) recommend products matching customer's preferences; 2) improve custom's intention towards recommended products; 3) best distinguish recommended products from products that do not match customer's preferences; and 4) reduce decision effort.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".