Movie-RNET: Best of Best Movie Recommendation via Deep Learning Networks from Multi-Format Data
Bibliographic record
Abstract
Abstract 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.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".