Tools
Tools
Adebo, Adelola (2020) A Natural Language Processing Approach to a Skincare Recommendation Engine. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (2MB) | Preview |
Abstract
Recommendation systems play a significant role in helping users to narrow their choice. Traditional recommendation techniques require the user's rating history to predict unknown ratings. Recently, a new line of recommendation system research has emerged, which seeks to exploit user reviews to serve as an alternative source of recommendation knowledge. In this study, we use the information included in the user reviews to develop a skincare recommendation system. The proposed methodology seeks to combine different review elements to address the issue of rating prediction. Another advantage of our proposed system is that it uses a deep neural network to recognize the commonalities between users and items. It also uses a word embedding and an additional Long-Short Term Memory encoder to learn better semantic word information instead of using traditional models such as bag-of-word models. The efficiency of the proposed framework in rating predictions was assessed using the Mean Squared Error Metric. Experimental findings show that the new recommendation method has performed better than the baseline approaches and can be used for e commerce purposes.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 18 Jan 2021 15:51 |
| Last Modified: | 18 Jan 2021 15:51 |
| URI: | https://norma.ncirl.ie/id/eprint/4379 |
Actions (login required)
 |
View Item |