7230ICT
Big Data Analytics and Social Media
Assignment Milestone 2 Specifications
Instructions
• Structure: Milestone 2 continues your Assignment case study that you started in
Milestone 1. Please refer back to Milestone 1 for the setting of the case study and advice
on how to complete this Assignment. Milestone 2 also includes a video presentation (see
details below).
• Due: See course site on Learning@Griffith for the due dates of each milestone.
• Late Submissions: An assessment item submitted after the due time on the due date set
by the Course Convenor, without an approved extension, will be penalised. Assessment
items submitted after the due time on the due date will be penalized at a rate of
5 percent (%) for each calendar day the assessment item is late. Assessment items
submitted more than seven calendar days after the due date will be awarded zero
marks.
• Extensions: If for any valid reason (e.g., being sick) you need an extension, you must
apply for an extension by the due date of the milestone through this online form:
https://www.griffith.edu.au/students/assessment-exams-grades/assessment-
applications
Milestone 2
Data Selection & Exploration (continued)
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 (Milestone 1)? (=> Lab 2.2)
[1.8 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)
[1.8 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 (Milestone 1)? (=> Lab 2.2)
[1.8 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)
[3.6 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)
[3.6 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)
[1.8 marks]
2.7) Build a decision tree and evaluate its performance in predicting whether a song is by
your artist/band. (=> Lab 5.2)
[2.25 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)
[1.8 marks]
Visualisation
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.)
[1.8 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.
[2.25 marks]
Analysis Review
2.11) Research and review other methods/algorithms for network analysis, machine
learning models, or visualisation. Compare them to the methods you used in these
milestones. Did you find a method that could give you better insights or more promising
results for your social media analytics? Explain why you think so.
[2-4 paragraphs, 2.5 marks]
Video Presentation
To complete your Milestone 2 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 both
Milestones (i.e., Milestone 1 and Milestone 2). 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]