An Approach for Aspect Extraction Using Double Embedding Technique based Machine Learning Model

Objectives: To perform aspect extraction for opinion mining of learner comments in the online teaching-learning scenario. Methods : A machine learning model is developed extraction. The authors collected dataset consisting around 5000 from Coursera and performed analysis on dataset. validate results, standard SemEval2014 used. Findings: For both contextualised non word embeddings, compiled results their two different datasets, viz., SemEval 2014 proposed provided an accuracy 92.78%. Novelty: first time literature, double embedding used Using domain-specific good but (using embedding) far superior accuracy. Keywords: Opinion Mining; Feature Extraction; Double Embedding; Learner Comments; Contextualised Embeddings