CZ4034 Project

CZ4034 - Information Retrieval

#HerHarryPotter #Fiction #Literature #HarryPotter #ApacheSolr #LordVoldemort #JKRowling #Potter

35 Pages • Essays / Projects • Year Uploaded: 2022

Through our project, our group has crawled for the latest customers’ reviews from the various filters and conditions available at the Amazon Customer Reviews webpages via the Google Chrome extension, Amazon Web Scraper. We then created a web interface, consisting of HTML and PHP files, and integrated them with the functionalities of the indexing software, Solr, where the required data manipulation, indexing and selection are carried out. After which, we proceed with data pre-processing using techniques such as merging and formatting the multiple CSV files of crawled data, removal of duplicated data, stemming, lemmatization, stop words removal and count vectorization. Following that, we performed our sentiment prediction using various classification models such as Naïve Bayes classifier, K-nearest Neighbour and Support Vector Machine. The models are then evaluated using evaluation metrics such as F-measure, precision and recall values and the results are compiled and analyzed. The powerful LDAvis library is used to visualize text data without difficulty. Lastly, we explored some innovations to enhance our classification such the use of GridSearch and k-fold Cross Validation and the use of ensemble classification model like Random Forest to compare with the models’ results.

This document is 20 Exchange Credits

More about this document:

	This document has been hand checked Every document on Thinkswap has been carefully hand checked to make sure it's correctly described and categorised. No more browsing through piles of irrelevant study resources.

	This is an Essay / Project Essays / Projects are typically greater than 5 pages in length and are assessments that have been previously submitted by a student for academic grading.

	What are Exchange Credits? Exchange Credits represent the worth of each document on Thinkswap. In exchange for uploading documents you will receive Exchange Credits. These credits can then be used to download other documents for free.

	Satisfaction Guarantee We want you to be satisfied with your learning, that’s why all documents on Thinkswap are covered by our Satisfaction Guarantee. If a document is not of an acceptable quality or the document was incorrectly described or categorised, we will provide a full refund of Exchange Credits so that you can get another document. For more information please read Thinkswap's Satisfaction Guarantee.

Studying with Academic Integrity

Studying from past student work is an amazing way to learn and research, however you must always act with academic integrity.

This document is the prior work of another student. Thinkswap has partnered with Turnitin to ensure students cannot copy directly from our resources. Understand how to responsibly use this work by visiting ‘Using Thinkswap resources correctly’.