ISSS608 2016-17 T1 Assign3 Lee Gwo Mey

Abstract

The purpose of this assignment is to explore and apply different visual analytics tools and techniques to analyze the available data and provide responses to the 3 tasks given
Summary of responses to the 3 tasks are

Task 1: IDs with Large Volume of Communication

There were 3 IDs with exceptionally high volume of communication compared to the rest.
ID_1278894 sent out messages at regular intervals. This ID could be used to administer the DinoFun World Apps and the Cindysaurus Trivia Game.
ID_839736, though recorded a high volume of communication, no fixed communication pattern was observed apart from a huge spike in volume on Sunday at 1200hrs.
ID_External was a common ID used to record communication between park visitor to an external party.

Task 2: Communication Patterns

Analyzing all communications at the 2 locations with Scott Jones' activities (Wet Land and Coaster Alley), no meaningful patterns could be seen due to the large number of communication data.
Analysis of the next 3 IDs with high volume of communication revealed that these 3 persons communicate to a large group of people for all 3 days. For ID_1116329, the communication with ID_1278894 was more frequent. It is likely for ID_1116329 to be used by DinoFun World Park Ambassador. For ID_1045021, communication was focused at Wet Land on Friday and Saturday, and in Tundra Land on Sunday. For ID_1250941, there was an increase in communication with ID_1278894 on Sunday, likely due to the discovery of vandalism on that day.
The overall changes in communication patterns at different locations on all 3 days showed that communications at the Entry Corridor and Wet Land areas were the highest at 9am. On Sunday, communications at Wet Land area remained high in the morning before tapering down in the afternoon.

Task 3: Time of Discovery

The vandalism at Creighton Pavilion (Wet Land; Attraction 32) was likely committed at around 9.30am to 11.30am on Sunday, 8 June 2014.
This is because there was no spike in communication messages at the Pavilion during 8am to 9am, when visitors entered the Pavilion.
However, when the Pavilion was re-opened at 11am, there was a sudden spike in communication messages.
Therefore, the vandalism was possibly discovered at around 11.30am.

Background of Case

DinoFun World is a typical modest-sized amusement park, sitting on about 215 hectares and hosting thousands of visitors each day. It has a small town feel, but it is well known for its exciting rides and events.

One event last year was a weekend tribute to Scott Jones, internationally renowned football ("soccer" in US terminology) star. Scott Jones is from a town nearby DinoFun World. He was a classic hometown hero, with thousands of fans who cheered his success as if he was a beloved family member. To celebrate his years of stardom in international play, DinoFun World declared "Scott Jones Weekend", where Scott was scheduled to appear in two stage shows each on Friday, Saturday and Sunday to talk about his life and career. In addition, a show of memorabilia related to his illustrious career would be displayed in the park's Pavilion. However, the event did not go as planned. Scott's weekend was marred by crime and mayhem perpetrated by a poor, misguided and disgruntled figure from Scott's past.

While the crimes were rapidly solved, park officials and law enforcement figures are interested in understanding just what happened during that weekend to better prepared themselves for future events. They are interested in understanding how people move and communicate in the park, as well as how patterns changes and evolve over time, and what can be understood about motivations for changing patterns.

The Tasks

Task 1 (Not More than 4 images and 300 words)

Identify those IDs that stand out for their large volume of communication. For each of these IDs,

Characterize the communication patterns you see
Based on these patterns, what do you hypothesize about these IDs?

Task 2 (Not More than 10 images and 1000 words)

Describe up to 10 communication patterns in the data. Characterize who is communicating, with whom, when and where. If you have more than 10 patterns to report, please prioritize those patterns that are most likely to relate to the crime.

Task 3 (Not More than 3 images and 300 words)

From this data, can you hypothesize when the vandalism was discovered? Describe your rationale.

Data Sets

DinoFunWorld_CommData.zip (3 days' in-app communication data)
DinoFunWorld_MoveData.zip (3 days' park movement data)
DinoFunWorld_LayoutMap.zip
DinoFunWorld_Website.zip (webpages of DinoFun World Park)

The communication data includes communications between the paying park visitors, as well as communications between the visitors and park services. In addition, the data also contains records indicating if and when the user sent a text to an external party.

Brief description of the Communication data fields are

Timestamp: date (yyyy-mm-dd) and time (hh:mm:ss AM/PM) of communication. Eg. 2014-06-06 08:03:19AM
From: identifier number that send out the communication message. Eg. ID_439105
To: identifier number that receive the communication message. Eg. ID_1053224
Location: location name where the communication message was sent/received. Eg. Kiddie Land

Visualization Software Used

JMP Pro 12
Tableau 10.0
Gephi 0.9.1

Exploratory Visualization Approach

Overview first, Zoom and Filter; then details-on-demand^[1]
Network Visualization and Analysis Process Model^[2]

Responses to Tasks

Task 1: IDs with Large Volume of Communication

Overview of IDs Communication Volume

Figure 1.1 shows an overview of the total number of messages sent and/or received by each ID.
The median number of messages per ID is 428.
The 3 IDs with exceptionally high number of messages compared to the rest are ID_1278894, ID_839736, and ID_External.

Communication Patterns of ID_1278894

Figure 1.2 shows the communication patterns of ID_1278894 at different locations for all 3 days and at different time.
The patterns revealed that messages were sent or received at hourly intervals in the afternoon (at 1200hrs, 1400hrs, 1600hrs, 1800hrs and 2000hrs).
No record of this ID_1278894 was found in the movement data.
As there was no physical movement records for ID_1278894, it is unlikely for this ID to be assigned to a phone or park device carried by the park visitor or park staff.
Majority of the messages were concentrated at the Entry Corridor. It is possible that this ID was used to send messages (eg. Welcome messages) to park visitors when they first entered the park, and for park visitors to register with the park's DinoFun World App.
Based on the communication patterns, ID_1278894 could be used to administer the DinoFun World App and Cindysaurus Trivia Game.

Communication Patterns of ID_839736

Figure 1.3 shows the communication patterns of ID_839736 at different locations for all 3 days and at different time.
Messages were sent and/or received throughout the day and at any time.
There was no noticeable pattern except for a huge spike on Sunday at 1200hrs. This is likely related to the discovery of vandalism.
No record of this ID_839736 was found in the movement data.
As there was no physical movement records for ID_839736, it is unlikely for this ID to be assigned to a phone or park device carried by the park visitor or park staff.
Based on the communication patterns, ID_839736 could be used as DinoFun Hotline or Helpdesk.

Task 2: Communication Patterns

Overview of Communication Patterns at Locations with Scott Jones' Activities

Figure 2.1 and 2.2 shows the communication networks of all IDs at Wet Land and Coaster Alley for all 3 days (Friday, Saturday and Sunday).
Location Wet Land and Coaster Alley were selected for analysis as Scott Jones' activities were concentrated at these 2 locations.
Display of Scott's memorabilia was at Attraction 32 Creighton Pavilion located in Wet Land.
Scott Jones' appearance at stage show was at Attraction 63 Grinosaurus Stage located in Coaster Alley.
No meaningful pattern was observed from Figure 2.1 and Figure 2.2, due to the large number of IDs analyzed.
The next exploration step would be to select the next 3 IDs with high communication volume for further analysis.

Communication Pattern of ID_1116329

ID_1116329 sent out high number of messages to large group of people for all 3 days.
ID_1116329 also communicated most frequently with ID_1278894 (DinoFun World App Service).
ID_1116329 could be DinoFun Tour Ambassador.

Communication Pattern of ID_1045021

ID_1045021 sent out high number of messages to large group of people for all 3 days.
Location of people who received the messages were in Wet Land on Friday and Saturday, and in Tundra Land on Sunday.

Communication Pattern of ID_1250941

ID_1250941 sent out high number of messages to large group of people for all 3 days.
On Sunday, more messages were made between ID_1250941 and ID_1278894, likely due to the discovery of vandalism on that day.

Changes in Communication Pattern on Friday, Saturday and Sunday

Figure 2.6 to Figure 2.8 shows the changes in communication patterns at different locations on Friday, Saturday and Sunday.
Communications at the Entry Corridor and Wet Land areas were the highest at 9am.
Possible reason could be the display of Scott's memorabilia at Wet Land (Creighton Pavilion) was first opened to visitors on Friday.
On Sunday, communications at Wet Land area remained high in the morning before tapering down in the afternoon.

Task 3:Time of Discovery

Spike in Communication Volume on Sunday

Figure 3.1 shows that there was a spike in communication volume on Sunday.
It is likely that the vandalism was discovered on Sunday, leading to an increase in communication activities.

Visitors Check-in Patterns at Creighton Pavilion

Figure 3.2 shows the visitors check-in patterns at Creighton Pavilion, the place of vandalism.
From the check-in patterns, there were no check-in at around 9am to 11am and 2pm to 3pm.
It can be inferred that the Pavilion was closed during the time when Scott Jones was at the Grinosaurus Stage Show.
Figure 3.2 also showed that there was no check-in on Sunday after 12 noon.
It is likely that the vandalism was discovered and the crime scene was closed for investigation.

Timing of Spike in Messages Sent to External

Figure 3.3 shows that there was a spike in messages sent to external parties at around 11.45am.
The communication pattern to external was analysed based on the assumption that visitors who were at the vandalism scene were likely to shared their first-hand discovery with friends who were not with them at the park.
Based on Figure 3.3, it can be deduced that the discovery was made around 11.30am by the first group of visitors to the Pavilion when it re-opened for operation.

References

^[1] Visual Information-Seeking Mantra [Shneiderman,1996]
^[2] Network Visualization and Analysis Process Model [Hansen, D. L. et. al. 2009]
^[3] YouTube Gephi Tutorials [1]
^[4] Visual Analytics Benchmark Repository [2]