Utilizing K-Means Clustering for the Detection of Cyberbullying Within Instagram Comments
Bibliographic record
Abstract
With the proliferation of social media platforms like Instagram, Twitter, and Facebook, the dissemination of information has undergone a significant transformation.Instagram, distinguished by its emphasis on visual media, has emerged as a platform of choice for photo and video sharing.Despite its popularity, the platform's vast reach renders it vulnerable to malevolent activities, including cyberbullying.While prior research has employed SVM, NBC, C45, and K-Nearest Neighbors for cyberbullying analysis, these studies predominantly focused on Twitter.This paper presents a novel approach, harnessing the power of K-means Clustering to identify instances of cyberbullying on Instagram.In this study, a labelled dataset is gathered and subjected to pre-processing steps, including case folding, tokenization, removal of stopwords, normalization, and stemming.Subsequently, the K-means Clustering algorithm is implemented and evaluated using 10fold cross-validation.The results indicate a threshold value of 1.0, an accuracy rate of 64.25%, a precision of 79.29%, and a recall of 59.88% in categorizing bullying words on Instagram.This research underscores the potential of the K-means algorithm in effectively distinguishing between bullying and non-bullying comments.A notable advancement of this paper is the integration of the two tf-idf weighting methods with the K-means clustering algorithm, thereby enhancing the accuracy in grouping comment data into cyberbullying and non-cyberbullying categories.
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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".