This summary is provided by the IPR Digital Media Research Center.

Dr. Yang Feng and Dr. Huan Chen examined which machine learning (ML) algorithms worked best to analyze consumer sentiment on YouTube.

A case study of 19,198 YouTube comments from the Always #LikeAGirl campaign was conducted. Researchers compared four traditional, supervised models (a machine learning method where models are trained with labeled data) to deep-learning, cloud-based AI models (a type of machine learning which relies on artificial neural networks) from Google and Amazon.

Key findings include:
1.) Deep-learning models from Google and Amazon had advantages over traditional machine learning algorithms.
— Training traditional supervised algorithms from scratch requires intensive coding, whereas using pre-trained models from Google and Amazon only require limited coding.
2.) Google’s models were not as consistent as Amazon’s, however, Google’s models were more transparent.
3.) Amazon’s model was the most efficient AI tool, achieving satisfactory learning results and using the shortest processing time to generate reliable results.
4.) Different algorithms can be used together to achieve the highest level of consumer insights and to better understand consumer behavior.

Find the original journal article here.

Heidy Modarelli handles Growth & Marketing for IPR. She has previously written for Entrepreneur, TechCrunch, The Next Web, and VentureBeat.
Follow on Twitter

Leave a Reply