PC Computer Science Sentiment Analysis and Clustering Questions
Im stuck on a Computer Science question and need an explanation. Question 1: Understanding peoples emotions is essential for businesses as technology allows customers to express their thoughts and feelings more openly than ever before. By automatically analyzing customer feedback from survey responses to social media conversations, brands are able to listen attentively to their customers, and tailor products and services to meet their needs. Below are the results of a sentiment analysis that analyzed over 4,000 online product reviews across 5 dimensions. Compare and contrast customers sentiment when considering only the Customer Service and Pricing dimensions? Question 2: On April 9th, 2017, United Airlines forcibly removed a passenger from an overbooked flight. The incident was filmed by other passengers on their smartphones and immediately posted to social media. One of the videos, posted to Facebook, was shared more than 87,000 times and viewed 6.8 million times just 24 hours later. This debacle was magnified by the companys initial (and dismissive) response. On Monday afternoon, United Airlines tweeted a statement from the CEO apologizing for having to re-accommodate customers. Cue public outrage you can imagine the field day on Twitter. How could have United Airlines used sentiment analysis in the immediate aftermath of the incident to help inform and/or shape their initial response? Question 3: Question 1 shows the results of a sentiment analysis conducted on product reviews. Sentiment is assessed in each of 5 dimensions. There is something not mentioned in Question 1 the dimensions where derived using cluster analysis. Describe the cluster identification process that could have been used discover the dimensionality of the products. Question 4: A small law firm is preparing for an important trial. From experience, firm management knows that their case will be assigned to 1 of 10 different judges. The firm knows that preparing a trial strategy for a specific judge is of paramount importance and is highly correlated with a successful outcome. However, the firm has finite resources and cannot possibly prepare 10 unique strategies. Each of the judges has been ranked (a numerical assessment on a scale of 1 to 7) in several dimensions such as legal sophistication, making instantaneous evidentiary decisions, rigorous intellectual analysis, etc. How could the firm use cluster analysis to reduce the number of trial strategies that they need to prepare? Question 5:The daily expenditures on food (X1) and clothing (X2) of five people are shown in the following table. Cluster analysis results of these individuals expenditures on food and clothing are in the following graph. Based on the table and cluster analysis results, please explain which individuals are more similar to each other and how would you explain the overall cluster analysis results.
