Analyzing the parallelization and structural impact of machine learning algorithms in social networks: a simulation-based approach
Bibliographic record
Abstract
Analyzing social media networks is crucial for understanding and uncovering common interests and characteristics among users within human societies. In this context, we simulated a simple application of human interaction in social networks, which involves users following others based on text similarity. We then investigated the effects of various machine learning (ML) algorithms employed in the applications to be used as recommendations to decision-making users. A novel agent-based social network simulator called distributed system and multinode processing is developed to assess the parallelization of the ML algorithms (i.e., K-means clustering, cosine similarity, support vector machine, multilayer perceptron) using bag of words (BoW) term frequency-inverse document frequency vectorization by evaluating their performance when executed in parallel across distributed heterogeneous resources. In addition, this simulator compares the effects of BoW with the Doc2Vec model on network structure by observing the differences in detected communities and resulting network graphs when a selected user follows the recommendations produced by an employed algorithm. Three real datasets were used in the experiments: Twitter, Scientific Research Papers, and Retail. This work's contribution is a unique in-house agent-based simulator developed to analyze the impact of common ML algorithms, including supervised and unsupervised learning, on social networks.
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 | 0.007 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
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".