Back

BFCI at #SMM4H 2023: Integration of Machine Learning and TF-IDF for Covid-19 Tweets Analysis

Nayel, H.; Ashraf, N.; Aldawsari, M.

2023-11-18 health informatics
10.1101/2023.11.18.23297862 medRxiv
Show abstract

Extracting information from texts generated by users of social media platforms becomes a crucial task. In this paper, we describe the systems submitted to the SMM4H shared tasks 1 and 2. The aims of these two tasks are binary and multi-class classification of English tweets. We developed a machine learning-based model integrated with TF-IDF as a feature extraction approach. Four classification algorithms have been implemented namely, support vector machines, passive-aggressive classifier, multi-layer perceptron and random forest. For task 1, the passive-aggressive classifier reported f1-score of 63.7%. For task 2, multi-layer perceptron reported f1-score of 71.4%.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.