The impact of sentiment analysis on decision outcomes - an empirical investigation
Bibliographic record
Abstract
A typical trade-off in decision-making is between the cost of acquiring information and the decline in decision quality caused by insufficient information. Consumers regularly face this trade-off in purchase decisions. Online product/service reviews serve as sources of product/service related information. Meanwhile, modern technology has led to an abundance of such content, which makes it prohibitively costly (if possible at all) to exhaust all available information. Consumers need to decide what subset of available information to use. Star ratings are excellent cues for this decision as they provide a quick indication of the tone of a review. However there are cases where such ratings are not available or detailed enough. Sentiment analysis - text analytic techniques that automatically detect the polarity of text - can help in these situations with more refined analysis. This study was performed in two interrelated phases. In the first phase the potential impact of Sentiment Scores (sentiment analysis outcomes) was investigated through a comparison between these scores with an already established numerical rating denoted as star ratings in three different domains. The results show that sentiment scores tend to fall into neutral areas and are not able to detect extremes that were reported to be more beneficial for information acquisition purposes. As a result, to use the current sentiment analysis results as a substitute for star ratings, a partial linear filter was applied to sentiment analysis results in a way to highlight the subtle differences away from the "neutral zone". In the second phase, the impact of the extended version of sentiment scores on decision outcomes was examined through a controlled experiment. The examined decision was a purchase decision and the information provided was pages of reviews annotated with extended sentiment scores on each paragraph. Human subjects were used in the experiment and controlled data gathering sessions was designed. Results suggest that female consumers may use sentiment scores on review documents without other comparison aids to increase their confidence level in their purchase decisions.
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 | 0.015 | 0.086 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".