MétaCan
Menu
Back to cohort
Record W4413230362 · doi:10.1142/s0219622025500798

A Deep Convolutional Neural Network Model to Predict Consumer Recommendations using Online Reviews

2025· article· en· W4413230362 on OpenAlex
Praphula Kumar Jain, Rajendra Pamula, Gautam Srivastava

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueInternational Journal of Information Technology & Decision Making · 2025
Typearticle
Languageen
FieldComputer Science
TopicSentiment Analysis and Opinion Mining
Canadian institutionsBrandon University
FundersCanadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada
KeywordsArtificial intelligenceComputer scienceConvolutional neural networkDeep learningMachine learningPredictive powerRecallData scienceProcess (computing)PerceptionArtificial neural networkConsumer behaviourPsychologyCognitive psychology

Abstract

fetched live from OpenAlex

Detecting consumer perception using online reviews is challenging. Artificial Intelligence (AI) techniques have the potential to understand human perception. Sensing human psychology is essential for business growth and selecting products or services in emerging markets. This paper proposes a Deep Convolutional Neural Network (DCNN) model to predict recommendations using consumer-generated online reviews. It reinforces the capability of Deep Learning (DL) models to consider two aspects of online reviews, qualitative and quantitative, and their combinations to predictive recommendations. We have collected online reviews of airline passengers from Skytrax with the objective. We have implemented various Natural Language Processing (NLP) techniques to process the qualitative contents of online reviews. Furthermore, pre-processed data with ratings on different service aspects feeds the proposed DCNN model. To validate the performance of the proposed model, we have evaluated different performance evaluation parameters such as precision, F-score, recall, and accuracy. The experimental analysis demonstrates that the DCNN model outperforms traditional Machine Learning (ML) models for predictive recommendations. Our research indicates the power of online reviews in understanding consumer intentions for emerging market growth.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.545
Threshold uncertainty score0.502

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0000.002
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.035
GPT teacher head0.365
Teacher spread0.330 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it