Overview | References | Data | Presentation | About us
In this work, a series of models are proposed with the aim of classifying Amazon reviews, more precisely related to the category "Pet supplies", trying to understand the degree of satisfaction of users, which can be positive, in case of high satisfaction, or negative, otherwise. This choice is justified by the fact that the reviews have a great influence on the purchasing behavior of consumers.
The first stages were developed around the cleaning of the data and the preprocessing of the analyzed texts.
In order to test the models, a division into training and validation sets was chosen, being the supervised approach. In total, six classification models were tested and it was decided to create a non-supervised task through a Sentiment Analysis (Opinion Mining), to see if the polarity of the reviews corresponded to the rating provided by the stars.
[1] Jianmo Ni, Jiacheng Li, Julian McAuley (2019), Empirical Methods in Natural Language Processing (EMNLP)
[2] Minqing Hu, Bing Liu (2004) Mining and summarizing customer reviews, Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery Data Mining, Seattle, Washington, USA
It was possible to have the necessary data thanks to Jianmo Ni
The complete Amazon Reviews Dataset can be found at the following link
Our slides presentation is available in the Slides folder.
Here we show only the cover:
⊜ Alessandro Borroni
- Current Studies: Data Science M.Sc. Student at Università degli Studi di Milano-Bicocca (UniMiB);
- Background: Bachelor degree in Business Economics at Università degli Studi di Milano-Bicocca (UniMiB).
⊜ Andrea Corvaglia
- Current Studies: Data Science M.Sc. Student at Università degli Studi di Milano-Bicocca (UniMiB);
- Background: Bachelor degree in Physics at Università degli Studi di Milano-Bicocca (UniMiB).
⊜ Mirko Giugliano
- Current Studies: Data Science M.Sc. Student at Università degli Studi di Milano-Bicocca (UniMiB);
- Background: Bachelor degree in Marketing, Business Communication and Global Markets at Università degli Studi di Milano-Bicocca (UniMiB).