Automatic extraction of the aspects of user reviews
Reserved master thesis
- Targeted audience
- AI Master
- Ability to read and understand papers written in English
- Ability to perform academic writing.
- Strong programming skills(Python; prefered)
- Lectures Information Retrieval or Information Mining
User reviews of products and services are providing very helpful information to the users which is effectively and efficiently satisfy their information needs. Traditionally, user reviews are not considered in the normal search operations. To solve this, we are developing more sophisticated approaches to retrieve and rank online items based on user reviews.
In order to make the retrieval and the ranking operations more reliable, we have to recognize the mentioned aspects of the reviews. This will make it easier for the search engines to decide whether the reviews are relevant to the user queries or not. In this thesis, the student has to investigate how can the aspects be identified and extracted using different techniques. This task differs from domain to domain. An effective technique within some domains is not necessarily working within others. In this research, we will be targeting specifically the domain of laptops products on Amazon.com. As an example, given this review about a laptop bought from Amazon: "I got this laptop yesterday, the screen was flickering heavily. And the wireless card doesn't work.", the mentioned aspects in this example are the screen and the wireless card.
This thesis includes the following phases:
- Literature scan. This should be done before the actual project starts. Here the student will be given some initial papers. Based on these papers, the student should collect more papers, perform a review of all the papers and prepare an oral presentation of 30 mins.
- Invistigating and developing an approach for performing the required task.