To build a predictive model to classify if a tweet contains sufficient depressive words to indicate depression state.

INSTRUCTIONS TO CANDIDATES

ANSWER ALL QUESTIONS

Objective:

• To build a predictive model to classify if a tweet contains sufficient depressive words to indicate depression state.

 

Brief background of data source: Part of the dataset is obtained from Twitter, combined with some derived attributes based on the original attributes from Twitter. The description of attributes in the dataset given is listed in Table 1. Further understanding of Twitter (if you are not familiar with Twitter’s social media platform), refer to the Twitter website.

 

Dataset: depression.xlsx (available in eLearn /Submissions/). Description of each attribute refer to Appendix Table 1.

 

Requirements and rules:

• You can choose to use any software and testing parameters to build the models.

• Predictive modelling techniques to choose: Regression and Decision Tree.

• You can choose to perform many tasks in the data preparation phase, for example, transformation, dummy variables, derived variables, deletion, and grouping/aggregation.

 

Assessment criteria (total 7 marks):

1. Data preparation (1 mark):

For the best model chosen, list the data preparation methods performed using the following tabular format. NOTE: If no data preprocessing task is performed, leave this table unfilled.

Attribute prepared Data preparation method(s) performed on the attribute Reason of performing the data preparation on the attribute

 

2. System results (1 mark):

• Screenshot the selected best model’s performance measurement result from the software you used (0.5 mark).

• Screenshot the diagram/process flow of your modelling from the software you used (0.5 mark).

 

NOTE: Save the answers for items 1 and 2 in ONE PDF file. Students will need to upload this PDF file through the relevant submission field in the eLearn /Submissions/ area.

 

3. Interpret and present the best model built (2 marks):

For the best model chosen, interpretation the model (1 mark) and show the model representation (1 mark). NOTE: Save the answer for items 3 through the relevant submission field in the eLearn /Submissions/ area.

 

4. Best model performance (3 marks):

Mark breakdown, i.e., how you can get the full 3 marks:

Best model accuracy % achieved Marks earn

>=75% 1

>=80% 2

>=85% 3

 

That means, if the best model does not achieve an accuracy of 75%, you will get 0 mark out of 3 marks. NOTE: Save the answer for items 4 through the relevant submission field in the eLearn /Submissions/ area.

 

Attachments:

Related Questions

. The fundamental operations of create, read, update, and delete (CRUD) in either Python or Java

CS 340 Milestone One Guidelines and Rubric  Overview: For this assignment, you will implement the fundamental operations of create, read, update,

. Develop a program to emulate a purchase transaction at a retail store. This  program will have two classes, a LineItem class and a Transaction class

Retail Transaction Programming Project  Project Requirements:  Develop a program to emulate a purchase transaction at a retail store. This

. The following program contains five errors. Identify the errors and fix them

7COM1028   Secure Systems Programming   Referral Coursework: Secure

. Accepts the following from a user: Item Name Item Quantity Item Price Allows the user to create a file to store the sales receipt contents

Create a GUI program that:Accepts the following from a user:Item NameItem QuantityItem PriceAllows the user to create a file to store the sales receip

. The final project will encompass developing a web service using a software stack and implementing an industry-standard interface. Regardless of whether you choose to pursue application development goals as a pure developer or as a software engineer

CS 340 Final Project Guidelines and Rubric  Overview The final project will encompass developing a web service using a software stack and impleme