MétaCan
Menu
Back to cohort
Record W4386835533 · doi:10.21203/rs.3.rs-3347773/v1

Movie-RNET: Best of Best Movie Recommendation via Deep Learning Networks from Multi-Format Data

2023· preprint· en· W4386835533 on OpenAlex

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.

Bibliographic record

VenueResearch Square · 2023
Typepreprint
Languageen
FieldComputer Science
TopicGenerative Adversarial Networks and Image Synthesis
Canadian institutionsFuture Earth
Fundersnot available
KeywordsOffensiveComputer scienceNormalization (sociology)Artificial intelligenceComputer visionMachine learningEngineeringOperations research

Abstract

fetched live from OpenAlex

<title>Abstract</title> Recommendation systems are desperately needed because of the large volume of information generated by the ever-growing use of social networks and the Internet. A recommendation system is essential since exploring the large collection can be time-consuming and difficult. In this research, a novel deep learning-based MovieRNet for best of best movie recommendation system using multi-format data has been proposed. Initially, the multiformat data such as reviews, emoji and trailer are gathered and pre-processed the reviews, emojis using normalization. The trailer videos are converted into frames and pre-processed using contrast stretching adaptive Gaussian Star filter for eliminating the noise artifacts. Pre-processed text is used as an input for BiGRU, which uses reviews to categorise films as offensive, non-offensive, or offensive but non-offensive. Pre-processed images are used as an input for Yolo v7, which uses features extracted from the movie trailer to categorise films as violent and non-violent. Pre-processed text is used as an input for BiGRU, which uses reviews to categorise films as offensive, non-offensive, or offensive but non-offensive. Pre-processed images are used as an input for Yolo v7, which uses features extracted from the movie trailer to categorise films as violent and non-violent. Jelly fish optimization algorithm is used for decision making by analyzing the outputs of the two neural networks to get the optimal prediction rate for time-to-time by updating the user profile with past references of the users. Recall, accuracy, specificity, precision, and F-measure were some of the criteria used to evaluate the proposed technique. The accuracy of the proposed method is improved by 9.6%, 7.8%, 3.5%, and 2.15% better than the existing LSTM-CNN, SRDNet, VRConvMF and SDLM methods respectively.

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)0.004
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Open science, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.829
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0050.014
Research integrity0.0000.003
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 head0.214
GPT teacher head0.405
Teacher spread0.191 · 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