An Enhancement in Machine Learning Approaches for Novel Data Mining Serendipitous Drug Usage to Reduce False Positive Rate from Social Media Comparing Word2vec Algorithm

Abstract

The aim is mining serendipitous drug usage to reduce the false-positive rate from social media. Materials and Methods: Two machine learning algorithms Knn classifier with the sample size = 12 and word2vec algorithm with sample size = 12. Results and Discussion: The knn algorithm has shown more accuracy of (93.91%) in reducing the false positive rates when compared with word2vec algorithm accuracy (87.50%). By using the G-power tool, the pre-test calculated with a g-power value = 80% and threshold 0.05% confidence interval of 95% mean and standard deviation. Conclusion: It is found that the knn classifier has more accuracy percentage when compared with the word2vec algorithm.