Skip to content

Course Project Topics⚓︎

  • TBU

Control Points⚓︎

All course project materials are supposed to be send to the professor's @hse email before the deadline. You can upload materials to your project github and send an email with github commit message and short description of the content.

Control Point 1 - Project Proposal⚓︎

Requirements: Text, containing:⚓︎

General structure of the Project Proposal is the following:

0.5-2 pages, describing what, how, using which data you are going to do.

  1. Title
  2. Abstract
  3. Introduction
  4. Main part
    • Literature Review
    • Anticipated SNA Methods
    • Expected Results
  5. Conclusion (optional)
  6. References
  7. Appendices (optional)

Control Point 2 - Project Equator⚓︎

Requirements: Presentation, containing:⚓︎

  1. Project repository inside https://github.com/SNA-23
  2. Project communication channel
  3. Project members
  4. Key Idea and description of the project (from CP1)
  5. The goal of the project and steps to reach the goal (from CP1)
  6. Roles in the team
  7. Current state of the project including;
    1. Description of the research dataset (Scraped or Found)
    2. Network design and framing (how nodes and edges were formed)
    3. Network description (centralities, diameter, density, network visualization)

The followingsteps of your project are supposed to be done at this moment:⚓︎

  1. Collection and preparation of data for analysis
  2. Description of the received data, distribution of the target variable

Control Point 3 - Project Defence⚓︎

Evaluation of the course project⚓︎

Project is evaluated according to the following criteria:

Title Description CP Deadline
Project Proposal Substantiation of the relevance of the chosen task and a brief literature review on the topic CP1 19.04.2024
Preprocessing and Data Loading Collection and preparation of data for analysis CP2 10.05.2024 15.05.2024
Descriptive statistics and centralities Description of the received data, distribution of the target variable CP2 10.05.2024 15.05.2024
Research hypothises validation Exploratory analysis and obtaining the structural features of the original array, classifier training, etc... CP3 01.06.2024
Interpretation of results Registration of the main results of the project as text of the CP paper and git repo. Explanation of the obtained results CP3 10.06.2024
Course Project presentation Speech & presentation at the final seminar CP3 15.06.2024

  • Sumbission date and time is taken from the date of delivery of the mail message to the professor's @hse.ru address (can be found at the official page). Late submission policy: -5% score per day. All submission deadlines are 23:59 GMT+3.

  • For the final project, students need to collect data and suggest a way to predict and/or model based on real network data. The assessment for the final project is set on a 10-point scale. Criteria for evaluating the final project.

Main results of the project Rating
Completely or partially collected data. A new prediction model has been implemented or a new simulation model has been built. A comparison with existing analogues was made, a quantitative/qualitative analysis of the results was carried out. Prepared a report on the work done in the format of a research article (research paper) or technical report (technical report), and reproducible code for the project. Excellent (10)
Completely or partially collected data. A new prediction model has been implemented or a new simulation model has been built. A comparison with existing analogues was made, a quantitative/qualitative analysis of the results was carried out. A short report on the work done and a reproducible code for the project has been prepared. Excellent (8-9)
Completely or partially collected data. The existing prediction model has been implemented. No model comparison or quantitative/qualitative analysis of results Good (6-7)
Completely or partially collected data. The prediction model has not been verified or is missing. Satisfactory (4-5)
Data on the project is not collected or not completely collected. The prediction model has not been verified or is missing. Unsatisfactory (0-3)