Social Media and Analytics Case Study

Overview

In this assignment, you are required to think about a case study, in which you can apply social media analytics to gain insight about how a certain music artist or band can improve their popularity. You will need to describe the setting for your case study, apply social media analytics using the tools introduced during the labs, and evaluate your findings and determine appropriate future actions.

You are required to use software for analysis and produce a written report. In the report, you need to explain your analysis findings. The report accounts for the majority of marks for each question. Simply pasting screenshots of your analysis outputs will not give you full marks. Accuracy and reproducibility of your code will be checked. You will also need to present your findings in a recorded video presentation and attend an interview to answer questions on your report/presentation.

• Choose data sources and data that are appropriate for your case study.
• Pay attention to how much data you retrieve and how frequently you retrieve data. If you try to get lots of data often, the APIs will impose a rate-limit on your account. However, you can still proceed after the rate-limit has ended.
• Use the software introduced in the labs (RStudio, Gephi, Tableau).
•  Add headings in your R scripts so that we can easily find the code related to each question.
•  Export all datasets as .RData files (so that we can re-run your code if needed).
•  Add screenshots of your results in the report. Include in the screenshot the code you wrote to produce that result. (Usually this would be the last line of code.)
•  Make plots/visualisations wherever possible, using R functions, Gephi, and Tableau. (Most results can be displayed as a plot/visualisation!)

Milestone

•  Choose a well-known artist or band. Assume you are the artist’s/band’s manager and want to help improve their popularity by using social media analytics.
• Your chosen artist/band should be well-known already so that there exists enough social media data that is somehow related to it. Otherwise, you may not be able to retrieve enough useful data for performing the analytical steps later.

Case Study Setting

1.1) Describe the artist/band you are managing. Make sure to reference your sources properly (don’t plagiarise). Use APA referencing style.

For example:

• How many years have they been active?
• How many albums & songs have they published? [1-2 paragraphs, 2 marks]

Data Selection & Exploration

1.2)  Collect data about your artist/band from Twitter. Make sure to choose keywords for data retrieval that are most relevant to your artist/band. However, try not to be too narrow. As a rough guide, you should retrieve at least 1000 tweets. List the keywords, explain your search strategy, and how much data you have collected.
(=> see Lab 2.1 for help)
[1.5 marks]

1.3)  List the top 5 most influential users for your artist/band. Find out what other interests/characteristics they have besides those related to your artist/band. Do these 5 have something in common? (=> Lab 2.1)
[2.5 marks]

1.4)  List the top 10 most important terms that appear together with your keyword(s) related to your artist/band. Explain the results. (=> Lab 2.1)
[1.5 marks]

1.5) Calculate how many unique user accounts there are in your dataset. Explain the code you have used for the calculation. What do the results tell you?
[2.5 marks]

Data Selection & Exploration

2.1)Use the Spotify API to extract data about your artist/band. For example:

•  How many years have they been active?
• How many albums & songs have they published?
•  With whom have they often collaborated?
• What are the prevalent features of their songs (e.g., valence)?

How does the Spotify data compare to the information you collected from other sources in Step 1.1? (=> Lab 2.2)
[2 marks]

2.2)Retrieve data relevant to your artist/band from YouTube. Which videos have the highest number of views and likes? Do you see a correlation between views and likes? (Your dataset may contain hundreds of videos, so it’s OK if you choose only a subset of those to get their statistics, in order to avoid hitting the rate-limit. However, you should get statistics for at least 5 videos.) (=> Lab 3.2)
[2 marks]

Text Pre-Processing

2.3)Perform text pre-processing and create a Term-Document Matrix for your Twitter data. What are the 10 terms occurring with the highest frequency? How are they different to your answer for Step 1.4? (=> Lab 2.2)
[2 marks]

Social Network Analysis

2.4) Perform centrality analysis by detecting degree centrality, betweenness centrality, and closeness centrality. Explain how relevant the results are to your artist/band. What are the actual degree, betweenness, and closeness centrality scores for your artist/band node in the network? Compare these scores to the scores for related artists. (=> Lab 3.1)
[4 marks]

2.5) Perform community analysis with the Girvan-Newman (edge betweenness) and Louvain methods. Explain how relevant the results are to your artist/band. Perform the community analysis also for related artists. Is their community structure similar?
(=> Lab 3.2)
[4 marks]

Machine Learning Models

2.6)Use sentiment analysis to identify how the public reacts to events and/or topics related to your artist/band. Provide a summary of public opinions (emotions, reactions). (=> Lab 5.2) [2 marks]

2.7)Build a decision tree and evaluate its performance in predicting whether a song is by your artist/band. (=> Lab 5.2)
[2.5 marks]

2.8)Use LDA topic modelling to identify some terms that are closely related to your artist/band. Find at least 3 significant groups of words that can be meaningful to your analysis. Explain your findings. (=> Lab 5.1)
[2 marks]

Visualization

2.9)Visualise your Twitter actor network in Gephi, with the node size determined by the number of followers for that actor. What insights can you extract from the visualisation? (This question is a little more difficult. Skip it if you’re unsure and come back later.Hint: Look at the vosonSML documentation. No further hints will be provided for the question.) [2 marks]

2.10) Create at least three charts from your datasets using Tableau and combine them together into a dashboard. Describe each chart in your dashboard and why you chose to include it. Explain the functionality of your dashboard and what insights you can obtain from it.
[2.5 marks]

Video Presentation

To complete your Milestone submission, you will need to record a video presentation of minimum 3 minutes and maximum 5 minutes duration. You should use PowerPoint slides or similar to show the results from your report. You will also need to record yourself while you are presenting and show your student ID at the beginning. Your presentation will need to cover your work from your Milestones. In the video, you should answer the following questions:

Evaluation

• Briefly introduce yourself (show your student ID) and your artist/band. What data have you collected (search terms, search parameters, amount of data)?[1 mark]
• What are the findings of your social media analytics? [2 marks]
• How could you refine your social media analytics? For example:
  • Could you use different data sources?
  • Could you choose different parameters?
  • Can you think of ways to obtain more relevant data? [2 marks]