Knowing the origin will help in finding the specific "deep paper" or documentation you need.
: Many datasets labeled "100K" are used to train classifiers (like RF) to detect spam or misinformation on Facebook. Key Source : Detecting Fake News on Social Media (ACM) . 4. Technical Specification: Random Forest (RF)
If your interest is in the algorithm itself applied to this scale: 100K RF FACEBOOK.xlsx
: Random Forest is preferred for 100K-row datasets because it handles high-dimensional data (many columns in an .xlsx) without the extensive preprocessing required by deep learning.
: Unlike "black box" deep learning, RF allows for "feature importance" analysis, showing exactly which Facebook metrics (e.g., shares vs. comments) are the strongest predictors. Knowing the origin will help in finding the
While the exact "deep paper" for that specific .xlsx file isn't publicly indexed, the following research areas represent the most likely "deep" academic context for such a dataset: 1. Facebook User Behavior & Prediction
: Predicting personality or "Likes" using ensemble methods. comments) are the strongest predictors
: Identifying 100,000 instances of automated or malicious accounts.