Applications Analyzing E-commerce Reviews with Large Language Models (LLMs): A Methodological Exploration and Application Insight
Bibliographic record
Abstract
The ubiquity of online shopping has transformed our daily lives, offering unparalleled convenience and enriching our purchasing experiences. It has become an indispensable part of our existence, allowing us to acquire everything from basic essentials to high-end luxury items with ease. Amazon, a leading e-commerce platform [1], employs two primary customer feedback mechanisms: the Star Rate (1-5) and detailed reviews. The Star Rate is a quick, convenient, and visually intuitive method for customers to score products, while reviews provide a more comprehensive description of the product and their shopping experience. These feedback mechanisms not only influence other users' purchasing decisions but also serve as a guide for businesses to adjust their offerings based on customer opinions, establishing a negative feedback adjustment mechanism.[2,3,4,5,6]. We introduce the innovative LLM model, commonly used in computer vision, into our NLP text analysis. Utilizing WORD2vec, we pass word vectors through classification functions to analyze pessimistic and optimistic sentiments. We then correlate these emotions with Star Rates, discovering a higher-order functional relationship between them.
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 | 0.007 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| 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".