1/20/2020

Problem Description

  • Prospective modern-day customers read the product reviews and feedback given by experts and other users on social media before the purchase of new gadgets.
  • This make companies cautious about their tech products and address the concerns and incorporate the recommendations of buyers in the next version of their products.
  • This is an analysis of the tech review and customer feedback on twitter, to get insights into what the customers seek from Apple’s iPhone Series.
  • To identify the areas of concern that need more focus.

Data Source

  • Primary Data Source: Twitter API
  • Data will be collected from twitter API using keywords such as iphone11, iphone11 pro, iphone11 pro max, selfies, #iphone11 and so on.
  • Twitter rate limits cap the number of search results returned to 18,000 every 15 minutes.
  • Since the data obtained from twitter is random text with a lot of irregularities and irrelevant content, we will have to clean the data before using it for further analysis.
  • Data cleaning will involve tasks such as elimination of duplicate tweets,removing the additional website/blog links etc.
  • The raw data will have many variables out of which only few can be used for our analysis. We will remove the irrelevant columns from the data for our final analysis.

Analytics Plan

  • We will be using topic modelling techniques to create topics based on the co-occurence of words in the document.
  • Topics are the set of words which appear more frequently together in a set of documents.
  • Each document (or tweet in our example) can contain multiple topics.
  • Then we will use text mining and sentiment analysis once the data is ready.

Evaluation Plan

  • The evaluation can include visualizations about: distribution of sentiments, frequency of the tweets, frequent terms in the tweets and geography-wise tweet analysis.
  • We will also be doing some competitor analysis. It is important to analyse the features of iPhone competitors to understand the area of improvement. The word frequency table will be explaining the aspect of competitor brand comparison.
  • Key takeaways from the word cloud could be: Competitors, camera feature, brands with similar range etc.