Analyzing Data from Social Media to Make Predictions Regarding the Behaviour Patterns of Customers
Bibliographic record
Abstract
Due to the rapid development of social media consumption, effective predictive models must be developed for estimating and predicting behaviour patterns of customers. To improve the accuracy of prediction in media consumer behaviour patterns, Bayesian optimized Long-Short Term Memory (LSTM) based mathematical Modelling is adopted. By enhancing LSTM model for hyperparameter modifications, the suggested model utilizes Bayesian optimization techniques to boost the accuracy of capturing temporal patterns within custom data of the media. For sequential data, Recurrent neural networks are renowned for their capability to model long and short-term relationships. With the help of Bayesian optimization mathematical model, hyperparameters are dynamically modified to match the distinct features of media usage data, enabling fine-tuning of the LSTM model. Integrating LSTM networks into Bayesian optimization allows a more precise and effective description of the intricate patterns observed in social media consumption behaviour. In comparison with Random Forests, RNN based Click Stream Model & Gradient Tree Boosting Method, the mathematical framework of proposed Bayesian optimized LSTM model reaches an accuracy of 99% and an improvement of 9.62%. This research supports the developing field of predictive analytics by offering an effective tool for understanding and predicting the constantly changing behaviour of media customers where both social media & technology are always changing with time.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".