Social Media Analytics and Visualisation

BIRMINGHAM CITY UNIVERSITY
FACULTY OF COMPUTING ENGINEERING AND THE BUILT ENVIRONMENT
COURSEWORK ASSIGNMENT BRIEF
CMP7202 Web Social Media Analytics and Visualisation
1
Coursework Assignment Brief
Postgraduate
Academic Year 2021 – 2022

Module Title:	Web Social Media Analytics and Visualisation
Module Code:	CMP7202
Assessment Title:	Assessment 1 (A1): Online Quiz Assessment 2 (A2): Coursework and Academic Report
Assessment Identifier:	Quiz and Coursework	Weighting: 100%
School:	Computing and Digital Technology
Module Co-ordinator:	Hossein Ghomeshi
Hand in deadline date:	• A1: Online Quiz on Week 6 • A2: Coursework and Report (two deliverables): 1.Presentation on Week10 2.Report and Code on Week 13 (Monday 9th May 2022 12:00 pm mid-day)
Return of Feedback date and format	20 working days from date of submission (see Moodle for details).
Re-assessment hand in deadline date:	12pm Mid-day on Monday 25th July 2022 Note: the reassessment work may be different.
Support available for students required to submit a re-assessment:	Timetabled revisions sessions will be arranged for the period immediately preceding the hand in date
NOTE:	At the first assessment attempt, the full range of marks is available. At the re-assessment attempt the mark is capped and the maximum mark that can be achieved is 50%.

AssignmentTutorOnline

BIRMINGHAM CITY UNIVERSITY
FACULTY OF COMPUTING ENGINEERING AND THE BUILT ENVIRONMENT
COURSEWORK ASSIGNMENT BRIEF
CMP7202 Web Social Media Analytics and Visualisation
2

Assessment Summary

Learning outcomes of this module will be assessed with 2
various in-semester assignment tasks.
A1: Online Quiz (20%)
Assessment 1 is an individual interactive quiz to be
conducted in week 6. The quiz will be 20 equally weighted
questions consisting of multiple choice, true/false, fill in
multiple gaps and short answers questions.
A2: Final Project (80%)
The purpose of this assessment is to give you experience
Assessment 2 is an individual assessment that consists of
two deliverables. Deliverable1 is a presentation on week
10 discussing findings from Part A of the final project. The
presentation should also give students early formative
feedback for the project progress. Deliverable 2 is the
final project code and report due on week 13.

3
IMPORTANT STATEMENTS
Standard Postgraduate Regulations
Your studies will be governed by the BCU Academic Regulations on Assessment, Progression and
Awards. Copies of regulations can be found at https://icity.bcu.ac.uk/AcademicServices/Information-for-Students/Academic-Regulations-2018-19
For courses accredited by professional bodies such as the IET (Institution of Engineering and
Technology) there are some exemptions from the standard regulations, and these are detailed in
your Programme Handbook
Cheating and Plagiarism
Both cheating and plagiarism are totally unacceptable, and the University maintains a strict policy
against them. It is YOUR responsibility to be aware of this policy and to act accordingly. Please
refer to the Academic Registry Guidance at https://icity.bcu.ac.uk/Academic-Registry/Informationfor-Students/Assessment/Avoiding-Allegations-of-Cheating
The basic principles are:
• Don’t pass off anyone else’s work as your own, including work from “essay banks”. This is
plagiarism and is viewed extremely seriously by the University.
• Don’t submit a piece of work in whole or in part that has already been submitted for
assessment elsewhere. This is called duplication and, like plagiarism, is viewed extremely
seriously by the University.
• Always acknowledge all of the sources that you have used in your coursework assignment
or project.
• If you are using the exact words of another person, always put them in quotation marks.
• Check that you know whether the coursework is to be produced individually or whether you
can work with others.
• If you are doing group work, be sure about what you are supposed to do on your own.
• Never make up or falsify data to prove your point.
• Never allow others to copy your work.
• Never lend disks, memory sticks or copies of your coursework to any other student in the
University; this may lead you being accused of collusion.
By submitting coursework, either physically or electronically, you are confirming that it is your own
work (or, in the case of a group submission, that it is the result of joint work undertaken by
members of the group that you represent) and that you have read and understand the University’s
guidance on plagiarism and cheating.
You should be aware that coursework may be submitted to an electronic detection system in order
to help ascertain if any plagiarised material is present. You may check your own work prior to
submission using Turnitin at the Formative Moodle Site. If you have queries about what
constitutes plagiarism, please speak to your module tutor or the Centre for Academic Success.
Electronic Submission of Work
It is your responsibility to ensure that work submitted in electronic format can be opened on a
faculty computer and to check that any electronic submissions have been successfully uploaded. If
it cannot be opened it will not be marked. Any required file formats will be specified in the
assignment brief and failure to comply with these submission requirements will result in work not
being marked. You must retain a copy of all electronic work you have submitted and re-submit if
requested.
4

Learning Outcomes to be Assessed:
1. Utilize various Application Programming Interface (API) services to collect data from different
social media sources.
2. Conduct basic social network and statistical analysis to render network visualisations
and to understand network characteristics.
3. Derive insights and discover patterns in structured social media data using methods
such as correlation, regression, and classification.
4. Extrapolate and analyse trends in unstructured-text data using natural language
processing methods such as sentiment analysis and topic classification.

Assessment Details:

Title:
Online Quiz
Type:
Online Assessment
Style:
Online quiz

Learning Outcomes to be Assessed:
• Understanding different techniques/skills in data analytics, visualisation and influence
in social media.
• Understanding of how to utilize various Application Programming Interface (API)
services to collect data from different social media sources.
• Conduct basic social network and statistical analysis to render network visualisations
and to understand network characteristics.
Rationale:
This assessment allows students to develop a deep understanding of social network sources
and characteristics, which is the core for understanding analytics and influence in social
media. The assessment also helps students to develop their problem solving, analytical and
time management skills.
Description:
The quiz will test students’ ability in the mastery of data collection, APIs, data types, ethics
and Influence in social media, Role of social media analytics in predicting the future. i.e.,
consumer behaviour, Network Structure, Basics of Social Network Analysis – at the network
level such as density, clustering classification, segmentation, degree distribution etc.; at the
vertices level – centrality, betweenness, closeness; at the sub-graph level – trades
communities – and network visualisation. The quiz is to be completed in 1-hour after which
students will be automatically timed-out.

Additional information:
For advice on writing style, referencing and academic skills, please make use of the Centre
for Academic Success: https://icity.bcu.ac.uk/celt/centre-for-academic-success
Workload: The quiz requires at least 10 hours of preparation/studying. Estimated number of
words in the quiz is 1000.
Transferable skills
The student will benefit from doing these assessments in developing both technical and
transferable skills, which include:
• Problem solving
• Programming skills
• Analytical skills
• Time management
• Project management
• Written communication skills

Title:
Assessment 2- Final project
Type:
Coursework and academic report
Style:
Practical coursework and academic report
Learning Outcomes to be Assessed:
• Utilize various Application Programming Interface (API) services to collect data from
different social media sources.
• Conduct basic social network and statistical analysis to render network visualisations
and to understand network characteristics.
• Derive insights and discover patterns in structured social media data using methods
such as correlation, regression, and classification.
• Extrapolate and analyse trends in unstructured-text data using natural language
processing methods such as sentiment analysis and topic classification.
Rationale:
This assessment provides a unique opportunity for the student to develop an end-to-end
project in social media analytics, starting from data collection and aiming to extract insights
and drive conclusions. The project handles social media analytics lifecycle which mimics
industry project’s setup.

Description:
Assessment 2 is an individual assessment which tests students’ ability to analyse social media
data using NLP techniques and statistical methods.
The deliverables for this assessment:
1. Presentation on week 10 on part A of the project. (20% presentation)
2. Final project code and report for both parts A and B on week 13. (60%)
The presentation will help students to focus on how to convey analytics insights to the general
audience. It will also help them in articulating their ideas and enhancing their communication
and presentation skills.
Presentation feedback is given by tutor and peers.
Through this assessment, the student is required to:
1. Extract social media data e.g., Twitter, Facebook, YouTube.
2. Clean the collected data.
3. Apply appropriate statistical techniques for topic modelling/NLP to detect a group of
words that best represent the information in the collection.
4. Process data to reveal new and interesting insights into the data, which may include
recurring patterns of words in the text that may translate to the interestingness of the
patterns.
5. Detect sentiments in the text that may determine the trends and topics.
6. Present your findings in a presentation and a technical report.
The assessment consists of 2 parts; part A focuses on statistical quantitative data analytics
while part B focuses on text data analytics. Details are as follows:
Part A: Statistical analysis
This part will focus on the statistical analysis of trends on social media. Students will use
APIs to collect data from Twitter and Facebook to answer the following questions:
1. What are popular trends on Twitter at the moment, either in the UK or worldwide?
Extract some insights from these trends such as: when it started in each place?
What devices are used to tweet? and what sources can you trust? Use plots, graphs
and maps to explain your insights.
2. Use one of the graph datasets available in Stanford Large Network Dataset
Collection (https://snap.stanford.edu/data/) or any other publicly available graph
dataset (you can also create your own graph), apply the following:
a. Find the most important nodes (individuals) in the network based on different
centrality measures,
b. Visualise your graph using one of centrality measures of your choice, and
c. Apply a Community Detection Algorithm to the graph, visualise the
communities and discuss your findings.

Use plots, graphs and maps to explain your insights.
Part B: Text mining
This part focuses on Topic modelling and sentiment analysis for social media analytics.
1. Choose an event/campaign that happened in the UK or worldwide recently (i.e.,
Brexit). Apply sentiment analysis to show users’ opinions about the topic on Twitter.
Represent your findings using statistical descriptive methods.
2. Access News APIs for articles related to the chosen event/campaign (Minimum of
5 articles)
• Perform all required cleaning and pre-processing on the articles.
• Perform basic descriptive analysis of the collected articles (time distribution, word
counts. etc).
• Use topic modelling techniques to discover key topics. Display your findings
using proper graphs, such as word cloud.
• Provide a summary on one of the news articles. Comment on the summarisation
quality.
A PDF file that contains your report of max 2000-word count (excluding your code chunks,
figures and appendices).
The file name has to be named as: STUDNETID_assessment2_report.pdf. The report
should include the following sections:
• Cover page (report title, student’s ID and name).
• Introduction: contains basic information of the data, the purpose of different tasks,
and other project backgrounds.
• Contents: The contents of the data report can be organised in many ways. If there are
specific questions were asked or tasks were required, it would be better to follow the
order of requirements to meet your readers’ expectations. This section should include
the following for each task:
o Description of your processes,
o Answer task questions,
o Justify your important decisions or assumptions, and
o Include limitations or tasks not accomplished.
• Summary and Conclusion
Additional information
For advice on writing style, referencing and academic skills, please make use of the Centre
for Academic Success: https://icity.bcu.ac.uk/celt/centre-for-academic-success
Workload: 30 hours for 2000 words report and a presentation of 1000 words.

Transferable skills
The student will benefit from doing these assessments in developing both technical and
transferable skills, which include:
• Problem solving
• Programming skills
• Analytical skills
• Time management
• Project management
• Verbal and written communication skills

Marking Criteria:
The Quiz score is based on the number of questions the student is able to get correctly. The
student’s score will be displayed on the teacher’s screen immediately after the submission
button is clicked.

Table of Assessment Criteria and Associated Grading Criteria

Assessment Criteria	Assessment 1 (online quiz)
Assessment 2 (report, presentation and code)
Task	1. Utilise various Application Programming Interface (API) services to collect data from different social media sources.	2. Conduct basic social network and statistical analysis to render network visualisations and to understand network characteristics.	3. Derive insights and discover patterns in structured social media data using methods such as correlation, regression, and classification.	4. Extrapolate and analyse trends in unstructured-text data using natural language processing methods such as sentiment analysis and topic classification.
Weighting:	20%	20%	30%	30%
Grading Criteria 0 – 29% F	No social media source has been utilised for data collection. No code has been provided. No data cleaning has been attempted. The report and presentation show no attempt to explain the collected data.	No code is provided for network analysis. No graphs are provided for network visualisation. The report has no discussion of network analysis. The presentation has no discussion of network analysis.	No attempts to apply statistical methods to extrapolate a meaningful understanding of the data. Very Poor quality of presentation. Non academic sources. No respect of time limit. Poor communication and presentation skills with no insights presented. No or a superficial interpretation of the results.	No examination of social media analytics. A superficial interpretation of the results. No clear solution provided for the underlying trends and topics. No code has been provided. No report submitted, or report shows little understanding of social data mining and the interpretation of the results. No articulation is provided to underpin the analysis.

30 – 39% E	Unsuccessful or no attempts for data collection from various social media sources. Incomplete or no running code has been provided. No or inadequate data processing has been attempted. The report and presentation show a superficial interpretation of the collected data.	Incomplete code is provided for network analysis. A very few incorrect /misleading graphs provided for network visualisation. The report has a very limited discussion of network analysis. The presentation contains a superficial discussion of network analysis and visualisation methods. The choice of networks and methods to analyse is very poor.	Very poor attempts to apply statistical methods to extrapolate a meaningful understanding of the data. Poor quality of presentation. No academic sources. Little/ no respect of time limit. Poor communication and presentation skills with very few insights presented.	Very Poor coverage of social media analytics. A poor interpretation of the results. Inaccurate or vague solution provided for the underlying trends and topics. Less than satisfactory report with incomplete or insufficient explanation of the adopted method(s) or lack of interpretation of the results. Very poor articulation to underpin the analysis and insights.
40 – 49% D	Poor attempts for data collection from various social media sources. Incomplete and poor-quality code has been provided. Incomplete data cleaning has been attempted. The report and presentation show limited and mostly incorrect interpretation of the collected data.	Code has some attempts for network analysis. However, wrong or incomplete output is presented. A very few graphs are represented for network visualisation, which mostly incorrect/ misleading. The report has some discussions of network analysis. However, unclear and/or inaccurate. The presentation has some elements of network analysis and visualisation. However incomplete and superficial. The choice of networks and analysis methods is poor but can be justified.	Poor attempts to apply statistical methods to extrapolate a meaningful understanding of the data. Poor quality of presentation with some findings. Few/poor academic sources. Little respect of time limit in the presentation. Poor communication and presentation skills with very few insights presented.	Results described with some lack of analysis, and it contains errors. A superficial interpretation of the results. A non-efficient solution provided for the underlying trends and topics. Code has been provided but incomplete and not clear with no comments and mostly no output. An adequate report with s good explanation of some of the adopted method(s) and fair interpretation of some of the results. Poor articulation to underpin the analysis and insights.

50 – 59%
C

satisfactory but
incomplete
attempts have
been demonstrated
for data collection
from various social
media sources.
Code has been
provided but
incomplete and
poorly commented.
Valid data cleaning
has been provided
but with some
errors.
The report and
presentation show
satisfactory but
incomplete
interpretation of the
collected data.

Code has some
attempts for network
analysis. However,
the output is
incomplete/ not
clear.
A good attempt to
generate graphs and
measures for
network
visualisation.
However, more
graphs and/or better
visualisation
methods are
expected.
The report has an
adequate
discussions of
network analysis.
However, more
details of the
insights are
required.
The presentation
has good attempts
for network analysis
and visualisation.
However mostly
incomplete.
The choice of
networks and
analysis methods is
adequate, however
better choices can
be made.

Satisfactory
attempts to apply
statistical methods
to extrapolate a
meaningful
understanding of the
data.
Fair quality of
presentation.
Little respect of time
limit.
Poor communication
and presentation
skills with few
insights presented.

Satisfactory coverage
of social media and
web analytics.
Results described but
it may lack some
analysis.
A non-efficient but
valid solution
provided for the
underlying social
media analytics.
Code has been
provided but
incomplete and
poorly commented.
The report may have
elements of good
explanation of the
adopted methods or
the interpretation of
the results.
Satisfactory
articulation to
underpin the analysis
and insights

60 – 69%
B

A successful but
incomplete
collection of data
from various social
media sources.
Code has been
provided which is
mostly complete
but sometimes
vague or inefficient.
Good data cleaning
has been provided
but can be
improved.
The report and
presentation show
a satisfactory
interpretation of the
collected data.

Code has very good
attempts for network
analysis. However,
the output is missing
some important
information.
Several graphs and
measures for
network visualisation
have been
generated.
However, some
graphs are very
complex to
understand or
incorrectly
visualised.
The report has an
adequate
discussions and
comparison of
network
characteristics.
However, some
insights are incorrect
and/or superficial.
The presentation
contains a good
discussion of
network analysis
and visualisation.
However, graphs
and discussions can
be improved.
The choice of
networks and
analysis methods is
good, however
better choices can
be made.

Good attempts to
apply statistical
methods to
extrapolate a
meaningful
understanding of the
data.
Good quality of
presentation.
Satisfactory
academic sources
are supporting
insights.
Time limit (almost)
not exceeded. Good
communication and
presentation skills
with some insights
presented.

Good coverage of
social media
analytics.
Sufficient
interpretation of the
results.
A valid solution
provided for the
underlying social
media analytics.
Code has been
provided which is
mostly complete with
satisfactory
comments and
structure.
The report has
elements of very
good explanation of
some of the adopted
methods or the
interpretation of the
results. Good
articulation to
underpin the analysis
and insights.

70 – 79%
A

A successful
collection of data
from various social
media sources with
some minor errors.
Code has been
provided which is
complete but
improvable. The
code is clearly
commented.
Good data cleaning
has been provided.
The report and
presentation show
a good
interpretation of the
collected data.

Code has complete
elements for network
analysis. However,
the code can be
improved for better
efficiency. Some
errors are produced.
Graphs and
measures for
network visualisation
have been
presented.
However, a few
graphs that are very
vague and/or not
well discussed.
The report has a
very good
discussions and
comparison of
network
characteristics.
However, some
more insights re
expected.
The presentation
contains a very good
discussion of
network analysis
and visualisation.
However, more
graphs and in-depth
discussion are
expected.
The choice of
networks and
analysis methods is
very good; however,
comparison is not
comprehensive.

Very good attempts
to apply statistical
methods to
extrapolate a
meaningful
understanding of the
data.
Very good quality of
presentation. Few
academic sources
supporting insights.
Time limit was
slightly exceeded.
Very good
communication and
presentation skills
with very good
insights presented.

Very good coverage
of social media
analytics.
Sufficient
interpretation of the
results.
Valid solution is
provided for the
underlying knowledge
discovery problem.
Code has been
provided and mostly
complete with clear
comments and
structure.
Very good report with
a good explanation of
most of the adopted
method(s).
Excellent
interpretation of the
results. Very good
articulation to
underpin most of the
analysis and insights.
More insights and
discussions were
expected.

80 – 89%
A+

A successful
collection of data
from various social
media sources.
Code is mostly
complete, efficient
and clearly
commented.
Complete data
cleaning has been
provided; still some
more minor
improvements are
required.
The report and
presentation show
a very good
interpretation of the
collected data.

Code has complete
elements for network
analysis. A few
parts of the code
can be improved for
better efficiency.
Most of the graphs
and measures for
network visualisation
have been
presented.
The report has
mostly in-depth
discussions and
comparison of
network
characteristics.
The presentation
contains an
excellent discussion
of network analysis
and visualisation.
More graphs are
expected to enhance
the discussion.
The choice of
networks and
analysis methods is
excellent;
comparison is well
presented. However,
need to be more
critical.

Effective application
of statistical
methods to
extrapolate a
meaningful
understanding of the
data.
In- depth analyses
strengths/weakness
of academic
argument with
insightful
conclusions.
Excellent
presentation of
arguments. An
overall naturally
coherent
presentation. Time
limits well respected.
Some presentation
elements need to be
improved.

Comprehensive
coverage of social
media analytics.
Excellent
interpretation of the
experiment and
results.
Appropriate solution
is provided that
reflects a good
understanding of
different techniques.
Code has been
provided in a very
good standard that is
mostly well structured
with clear comments.
Very good report with
mostly complete
explanation of the
adopted method(s)
Very good
discussions of the
interpreted results.
Very good articulation
to underpin the
analysis and insights.

90 – 100%
A*

Accurate and
efficient collection
of data from
various social
media sources.
Code is complete,
efficient and clearly
commented.
Complete data
cleaning has been
provided.
The report and
presentation show
an excellent and
comprehensive
interpretation of the
collected data.

Code for network
analysis is complete,
efficient and error
free.
All graphs and
measures for
network visualisation
have been well
presented.
The report has an
impressive in-depth
discussions and
comparison of
network
characteristics.
The presentation
contains an
outstanding
discussion of
network analysis
and visualisation.
The choice of
networks and
analysis methods is
excellent; a critical
comparison is well
presented.

Excellent application
of statistical
methods to
extrapolate a
meaningful
understanding of the
data.
Exclusive focus on
research papers. In
depth analyses
strengths/weakness
of academic
argument with
insightful
conclusions.
Excellent
presentation of
arguments. An
overall naturally
coherent
presentation. Time
limits well respected.

Excellent coverage of
social media
analytics.
Excellent
interpretation of the
experiment and
results.
Very efficient
solutions are
provided that reflect a
good understanding
of different
techniques.
Code has been
provided in high
standard that is well
structured with clear
comments.
Excellent report with
excellent explanation
of all of the adopted
method(s) and
excellent
interpretation of the
results. Very good
articulation to
underpin the analysis
and insights.

Submission Details:

Format:
Assessment 1: The submission is by attempting the online quiz in class.
Assessment 2: The submission is by submitting a code and report on Moodle.

Regulations:
• The minimum pass mark for a module is 50%
• Re-sit marks are capped at 50%
Full academic regulations are available for download using the link provided above in the IMPORTANT
STATEMENTS section
Late Penalties
If you submit an assessment late at the first attempt, then you will be subject to one of the
following penalties:

• if the submission is made between 1 and 24 hours after the published deadline the
original mark awarded will be reduced by 5%. For example, a mark of 60% will be
reduced by 3% so that the mark that the student will receive is 57%.
• if the submission is made between 24 hours and one week (5 working days) after
the published deadline the original mark awarded will be reduced by 10%. For
example, a mark of 60% will be reduced by 6% so that the mark the student will
receive is 54%.
• if the submission is made after 5 days following the deadline, your work will
be deemed as a failure and returned to you unmarked.
The reduction in the mark will not be applied in the following two cases:
• the mark is below the pass mark for the assessment. In this case the mark achieved
by the student will stand
• where a deduction will reduce the mark from a pass to a failure. In this case the mark
awarded will be the threshold (i.e., 50%)
Please note:
• If you submit a re-assessment late then it will be deemed as a failure and
returned to you unmarked.

Feedback:
Assessment 1: online quiz instantaneous score
Assessment 2:
– Presentation feedback will be provided on the presentation day. Feedback is provided
from both
instructor and peers.
– The practical code will be corrected, and report will be marked.
Marks and Feedback on your work will normally be provided within 20 working days of its
submission deadline.
Where to get help:
Students can get additional support from the library support for searching for information
and finding academic sources. See their iCity page for more information:
http://libanswers.bcu.ac.uk/
The Centre for Academic Success offers 1:1 advice and feedback on academic writing,
referencing, study skills and maths/statistics/computing. See their iCity page for more
information: https://icity.bcu.ac.uk/celt/centre-for-academic-success
Link to My Assignment Planner tool: http://library.bcu.ac.uk/MAP2/freecalc-mail/
17
Fit to Submit:
Are you ready to submit your assignment – review this assignment brief and consider
whether you have met the criteria. Use any checklists provided to ensure that you have
done everything needed.
Please use the following check list for each assessment:

Assignment
Tip Sheet

Assignment Checklist
Run through this simple tick list before submitting your work!
A2 presentation:

Item	Action	Done?
1	Have you prepared your presentation?
2	Have you written your name and ID on the presentation first slide?
3	Have you answered all the question in the assessment specifications?
4	Have you included figures and graphs to support your answers?

A2 final report and code:

Item	Action	Done?
1	Have you followed all the steps outlined in ‘Assessment Details’?
2	Have you included a cover page of your assessment report?
3	Have you proofread your report?
4	Have you answered all the question in assessment specifications in your code and in the report?
5	Have you included figures and graphs to support your answers?
6	Have you checked the word count against assessment specifications?
7	Have you checked your code is running and outputs are displayed correctly?

Referencing and Originality
18
Your work will be subjected to checks to ensure it is not derivative of other works. Works found
to be derivative may leave you subject to penalties, including in extreme cases, expulsion from
the University.

Item	Action	Done?
1	All images and tables are fully referenced
2	I have not copied any material from anywhere else. All sentences have been paraphrased into my own words.
3	All references appear in the references section at the end of the presentation.
4	All references are cited in the text in the form of (author, year). See https://www.bcu.ac.uk/library/services and-support/referencing for more details.
5	If I have used quotes, these are fully referenced, appear in quotation marks and form only a small part of my report.

Social Media Analytics and Visualisation

Get 25% off your order