MET CS688 Final Project Description You have used PubMed dataset in your home-works. You need to analyze this dataset and write a research report to answer following questions, about these keywords: “Obesity”, “Cancer”, “Covid-19”, “wearable”, “mental health”, “influenza”. 1. What are some knowledge that can be extracted from trajectory of these research works in a duration of ~10 years. 2. What are most frequent focus of academia based on research keyword, and how does this focus changed over the year. 3. What are the sentiments about particular keywords, which one are positive, which one are negative. What is the sentiment trajectory during 10 years period? 4. What are similar research works that can be identified by algorithm (you should use both clustering and association rule mining for the title of articles). 5. You can write your own findings based on your experience while working with this dataset. NOTES: (1) you should prepare a research report for at least three pages. The text of your report should include “Times new Roman” font with size 12, and page margin not more than 1 inches from side of the page. (2) You should send your code along with your report, but not inside your report. Including any code inside your report is not acceptable and this mistake will cause reduction in your final grade. Your report must include visualization, especially the one we have learned in the class or your homework. (3) While writing your report you should write about the (i) statistical test, (ii) feature engineering (even if it is simplest one like column selection) (iii) sentiment analysis, (iv) clustering, (v) theme extraction, and (v) association rule mining methods, you have used to answer above research questions. (4) It should be written as a research report. Here is a good link to help you writing a research report: https://writing.wisc.edu/handbook/assignments/planresearchpaper/ https://fastessay.com/blog/7-steps-in-writing-a-research-paper-enjoy-your-student-life/ (5) Any collaboration with other student is forbidden and if we detect it, we will assume it as cheating. (6) The deadline to deliver your final project is on 10th Dec 2020.
欢迎咨询51作业君