Difference between revisions of "Group03 proposal"

From ISSS608-Visual Analytics and Applications
Jump to navigation Jump to search
Line 35: Line 35:
 
Libraries typically develop surveys for 3 reasons: to gauge user satisfaction, to assess users' needs (usage), or to learn more about outcomes—that is, the end results of using the library. A fourth purpose of surveys is to gather demographic information about library users. The purpose of our project is in line with these needs, where we will build broad visualizations, identify areas to delve into and propose solutions/better outcomes.  
 
Libraries typically develop surveys for 3 reasons: to gauge user satisfaction, to assess users' needs (usage), or to learn more about outcomes—that is, the end results of using the library. A fourth purpose of surveys is to gather demographic information about library users. The purpose of our project is in line with these needs, where we will build broad visualizations, identify areas to delve into and propose solutions/better outcomes.  
  
Data Preparation – Study the dataset provided and clean the data for conducting analysis of the Survey Results  
+
'''Data Preparation''' – Study the dataset provided and clean the data for conducting analysis of the Survey Results  
  
Analysis of Survey - Deep dive into the survey   
+
'''Analysis of Survey''' - Deep dive into the survey   
 
+
# Numbered list item
+
* Exploratory Data Analysis - Perform EDA to analyze the survey results and come up with some interesting findings.
Exploratory Data Analysis - Perform EDA to analyze the survey results and come up with some interesting findings.  
+
 
# Numbered list item
+
* Sentiment Analysis- Analysis of the overall sentiment of the comments provided in the survey, leading to positive/negative emotions about the library
Sentiment Analysis- Analysis of the overall sentiment of the comments provided in the survey, leading to positive/negative emotions about the library  
+
 
# Numbered list item
+
* Model Building- Build a model using LCA / Neural Networks to understand which factors are more important to people from different study areas  
Model Building- Build a model using LCA / Neural Networks to understand which factors are more important to people from different study areas  
 
  
Visualizations – Create Visuals to demonstrate the findings of the Survey  
+
'''Visualizations''' – Create Visuals to demonstrate the findings of the Survey  
  
Implementation – Build R-Shiny app and provide technical report  
+
'''Implementation''' – Build R-Shiny app and provide technical report  
  
 
   
 
   
Line 58: Line 57:
 
== Data Description ==  
 
== Data Description ==  
  
Data Field  
+
{| class="wikitable"
 
+
|-
Description  
+
! Data Field !! Description !! Data Type
 
+
|-
Data Type  
+
| ResponseID || ID of the respondent || Numeric
 
+
|-
ResponseID  
+
| Campus || Name of the Library || Categorical
 
+
|-
ID of the respondent  
+
| Position || Designation || Categorical
 
+
|-
Numeric  
+
| StudyArea || Major area of study, research or teaching || Categorical
 
+
|-
Campus  
+
| ID || Whether an International (non-exchange) student or not || Categorical
 
+
|-
Name of the Library  
+
| I01-I26 || Survey Questions Category 1 || Ordinal
 
+
|-
Categorical  
+
| P01-P26 || Survey Questions Category 2 || Ordinal
 
+
|-
Position  
+
| Comment1 || Suggestions for improvement or any other comments about the Library || String
 
+
|-
Designation  
+
| HowOftenL || How frequently the library is visited || Ordinal
 
+
|-
Categorical  
+
| HowOftenC || How frequently the campus is visited || Ordinal
 
+
|-
StudyArea  
+
| HowOftenW || How frequently the library resources are accessed || Ordinal
 
+
|-
Major area of study, research or teaching  
+
| NA01-NA26 || Survery Questions Category 3 || Ordinal
 
+
|-
Categorical  
+
| NPS1 || Likelyhood of recommending the library service to other students || Ordinal
 
+
|}
ID  
 
 
 
Whether an International (non-exchange) student or not  
 
 
 
Categorical  
 
 
 
I01-I26  
 
 
 
Survey Questions Category 1  
 
 
 
Ordinal  
 
 
 
P01-P26  
 
 
 
Survey Questions Category 2  
 
 
 
Ordinal  
 
 
 
Comment1  
 
 
 
Suggestions for improvement or any other comments about the Library  
 
 
 
String  
 
 
 
HowOftenL  
 
 
 
How frequently the library is visited  
 
 
 
Ordinal  
 
 
 
HowOftenC  
 
 
 
How frequently the campus is visited  
 
 
 
Ordinal  
 
 
 
HowOftenW  
 
 
 
How frequently the library resources are accessed  
 
 
 
Ordinal  
 
 
 
NA01-NA26  
 
 
 
Survery Questions Category 3  
 
 
 
Ordinal  
 
 
 
NPS1  
 
 
 
Likelyhood of recommending the library service to other students  
 
 
 
Ordinal  
 
 
 
 
   
 
   
  
Line 150: Line 95:
 
       Tools used - Rstudio: https://rstudio.com/  
 
       Tools used - Rstudio: https://rstudio.com/  
  
Packages
+
{| class="wikitable"
 
+
|-
Purpose  
+
! Packages !! Purpose
 
+
|-
Shiny()  
+
| shiny() || Package for creating the R shiny interface
 
+
|-
Package for produce their R shiny interface  
+
| topicmodels() || Package for Topic Modelling
 
+
|-
Topicmodels()  
+
| ggplot2() || Package for creating the Charts & Visualization
 
+
|-
Package for Topic Modelling  
+
| dplyr() || Package for Data Manipulation
 
+
|-
Ggplot2()  
+
| sentimentanalysis() || Package for Performing Sentiment Analysis on Remarks  
 
+
|-
Package for produce their charts and visualizations
+
| wordcloud() || Package for creating Word Clouds
 
+
|}
Dplyr()  
 
 
 
Package for data manipulation.
 
 
 
SentimentAnalysis()  
 
 
 
Package for Performing Sentiment Analysis on Remarks  
 
 
 
WordCloud()  
 
 
 
Package for Creating Wordclouds
 
 
 
 
   
 
   
  
 
== Members – Milestones ==   
 
== Members – Milestones ==   
  
Joshua Lam Jie Feng  
+
'''Joshua Lam Jie Feng'''
  
Exploratory Data Analysis  
+
* Exploratory Data Analysis 
 +
 +
* Network Analysis  
  
Network Analysis
+
'''Karthik Nityanand'''
  
Karthik Nityanand
+
* Exploratory Data Analysis 
  
Exploratory Data Analysis  
+
* Latent Class Analysis  
  
Latent Class Analysis  
+
'''Shreyansh Shivam'''
 +
 
 +
* Exploratory Data Analysis
  
Shreyansh Shivam
+
* Topic Modelling  
 
 
Exploratory Data Analysis
 
 
 
Topic Modelling  
 
  
 
   
 
   
Line 206: Line 139:
 
   
 
   
  
https://www.lrs.org/library-user-surveys-on-the-web/  
+
* https://www.lrs.org/library-user-surveys-on-the-web/  
  
https://greenhill-library.org/wp-content/uploads/2016/12/public-survey-analysis-2016.pdf  
+
* https://greenhill-library.org/wp-content/uploads/2016/12/public-survey-analysis-2016.pdf  
 
+
https://www.tidytextmining.com/index.html
+
* https://www.tidytextmining.com/index.html

Revision as of 19:50, 29 February 2020

Overview/Motivation

Singapore Management University (SMU) has 2 physical libraries – the Li Ka Shing Library and Kua Geok Chee Library, which aim to provide plethora of information to drive intellectual exchange and creation of knowledge in the SMU community. Every 2 years, the SMU library will conduct a user survey of faculty, staff and students to collect information to gauge its performance in providing library services to the community, based on 4 categories of assessment:

  • Communication
  • Service delivery
  • Facilities and equipment
  • Information resources

Current reports generated from responses from the Library Survey in 2018 are mainly displays of survey responses with highlighting of what library users consider as most important, with aggregate statistical results generated, but we feel there is potential for more insight to be discovered from the data.

Our project hopes to create a R Shiny application in order to revisit and uncover insights from Singapore Management University (SMU) Library Survey 2018 data to uncover insights in the perception of importance of aspects of library services and facilities, as well as the library performance based on these matrices, based on inputs from faculty, staff and students. As the survey questions are being reused for the SMU Library Survey 2020, there is potential for re-use of the R Shiny application for this year.


Project Objectives

Exploratory data analysis in order to generate meaningful insights beyond aggregated statistical data and uncovering the factors considered important by library users.

Using text analytical techniques and topic modelling to analyses free text responses and sentiments of survey responders

Use latent class analysis and association & network analysis to determine relationships between factors used to benchmark performance and provision of library facilities.


Data Source & Inspiration References

Proposed Story/Dashboard

Libraries typically develop surveys for 3 reasons: to gauge user satisfaction, to assess users' needs (usage), or to learn more about outcomes—that is, the end results of using the library. A fourth purpose of surveys is to gather demographic information about library users. The purpose of our project is in line with these needs, where we will build broad visualizations, identify areas to delve into and propose solutions/better outcomes.

Data Preparation – Study the dataset provided and clean the data for conducting analysis of the Survey Results

Analysis of Survey - Deep dive into the survey

  • Exploratory Data Analysis - Perform EDA to analyze the survey results and come up with some interesting findings.
  • Sentiment Analysis- Analysis of the overall sentiment of the comments provided in the survey, leading to positive/negative emotions about the library
  • Model Building- Build a model using LCA / Neural Networks to understand which factors are more important to people from different study areas

Visualizations – Create Visuals to demonstrate the findings of the Survey

Implementation – Build R-Shiny app and provide technical report


Project Timeline

Data Description

Data Field Description Data Type
ResponseID ID of the respondent Numeric
Campus Name of the Library Categorical
Position Designation Categorical
StudyArea Major area of study, research or teaching Categorical
ID Whether an International (non-exchange) student or not Categorical
I01-I26 Survey Questions Category 1 Ordinal
P01-P26 Survey Questions Category 2 Ordinal
Comment1 Suggestions for improvement or any other comments about the Library String
HowOftenL How frequently the library is visited Ordinal
HowOftenC How frequently the campus is visited Ordinal
HowOftenW How frequently the library resources are accessed Ordinal
NA01-NA26 Survery Questions Category 3 Ordinal
NPS1 Likelyhood of recommending the library service to other students Ordinal



Tools & Packages

      Tools used - Rstudio: https://rstudio.com/ 
Packages Purpose
shiny() Package for creating the R shiny interface
topicmodels() Package for Topic Modelling
ggplot2() Package for creating the Charts & Visualization
dplyr() Package for Data Manipulation
sentimentanalysis() Package for Performing Sentiment Analysis on Remarks
wordcloud() Package for creating Word Clouds


Members – Milestones

Joshua Lam Jie Feng

  • Exploratory Data Analysis
  • Network Analysis

Karthik Nityanand

  • Exploratory Data Analysis
  • Latent Class Analysis

Shreyansh Shivam

  • Exploratory Data Analysis
  • Topic Modelling


References