This tool is designed to assist IT students in exploring different entry-level positions and then view the specific courses at GGC which would provide the entry-level skills for each position they are interested in. The scope of this project for Spring 2021 is to gather job listing datasets, clean and filter the initial datasets, manually test the project's goal, and statistically analyze data about job skills. The result of the project is that we have proven that our process works and that important job-skills data can be captured, filtered, displayed, and can be ultimately used in an application. Significant further development is required. Other IT students at GGC will have the opportunity to provide more research into different entry-level positions and provide the actual development of the Web/Mobile application to create a highly-beneficial working tool.
Spring 2025 Scope: Further develop the website tool by cleaning, analyzing, and creating visualizations from webscraped job posting sites such as LinkedIn, Glassdoor, and Indeed.com. These results will be used to attain the top 5-10 jobs and their correlating primary technical and soft skills depending on major or field. The user selected job/skill will result in the tool displaying courses that teach those necessary skills, ensuring the student will learn the skills necessary to attain their dream job. The team is working to update and revamp the current website to be more interactive and dynamic for users.
Updates Fall 2025: GrizzlyPaths is a web application that is meant to help upcoming IT majors by showing them a road map of skills that will be required for jobs in the desired industry. Our focus is on creating a road map that will display 10 job titles that will be displayed based on the occurrence within multiple job searching websites. As they choose the job, hard and soft skills will then be displayed based on importance from a variety of companies. Those skills will have corresponding courses at Georgia Gwinnett College that students must attend.
Fall '25: Fall 2025 Presentation
Spring '25: Spring 2025 Presentation
Fall '23: Fall 2023 Presentation
Spring '23: Grizzly Insights Screencast
Summer '21: Hugh Smith Presentation
Spring '25: Grizzly Paths Website Link
Spring '23: Grizzly Path
Spring '25: Grizzly Paths '25 Notebook
Fall '23: Fall 2023 Notebook
Spring '23: Grizzly Insights Notebook
Fall '25: Fall 2025 Final Report
Spring '25: Spring 2025 Final Report
Fall '23: Fall 2023 Final Report
Spring '23: Grizzly Insights Final Report
- Students: Sidibaba Simpara - Project Manager & UI/UX design, Hieu Do - Lead Programmer & Documentation Lead, Charles Sarpong - Testing Lead, William Chokbengboune - Data Modeler & Client Liaison
- Advisor: Dr. Anca Doloc-Mihu
- Team Flyer
- Team Photo with Clients
- Coding Documentation
- Student: Michelle Webb - Data Analyzer/Project Manager, Nikhita Nikhita- Visualization/Project Documenter, Krishan Bhalsod - Data Modeler/Data Analyzer/data cleaning/collection, Lucas Leon Visualization/Client_Liason
- Advisor: Dr. Anca Doloc-Mihu, Assistant Professor of Information Technology
- Students: Sam Downs
- Advisor: Dr. Anca Doloc-Mihu
- Students: Anel Coralic, Sam Downs, Ashley Mendez
- Advisor: Dr. Anca Doloc-Mihu, Assistant Professor of Information Technology
- Student: Michael Murillo Martinez
- Advisor: Dr. Anca Doloc-Mihu, Assistant Professor of Information Technology
- Student: Hugh Smith
- Advisor: Dr. Anca Doloc-Mihu, Assistant Professor of Information Technology
- Grizzly Paths Poster, April 17, 2025 at GGC
- Team Photo for Honorable Mention awarded - Spr '25
- Grizzly Insights Poster, April 13, 2023 at GGC
- 2nd Place Poster https://ggc-stars.github.io/posters/, April 8, 2021 at GGC
- Grizzly Insights Presentation, April 27, 2023 at GGC
- CREATE Symposium, April 29, 2021, GGC
- ITEC 2140 Introduction to Java, Profession Xin Xu, April 27, 2021
- ITEC 2140 Introduction to Java, Profession Xin Xu, April 28, 2021
- Backend: Firebase
- Frontend: HTML/CSS, JavaScript
- Project Dependencies: React + Vite, Jest, Vitest, Boostrap, Paraphase, CSV-parser, Chart, Firebase SDK, Firebase CLI
- Version Control: Git & Github
- Project Management: Jira
- Colab Notebook
- PowerBi
- Web Scraping Site - Bright Data
- Python, Vue.js, JSON, HTML/CSS
- Jupyter Notebook
- Python, JavaScript, JSON
- Web Scraper Google Chrome Extension
- Web Scraper YouTube Tutorial
- Jupyter Notebook
- Google Colab
- Python, HTML, JavaScript, CSS
I utilized the website kaggle.com to obtain the job listing datasets, Microsoft Excel for data cleansing, Google Drive for online file location, and Google Colab Notebook for python development, data analysis, and display.
- https://www.kaggle.com/
- https://www.microsoft.com/en-us/microsoft-365/excel
- https://drive.google.com/drive/my-drive
- https://colab.research.google.com/notebooks/intro.ipynb?utm_source=scs-index
- Technical Results: https://github.com/GGC-DSA/itskills/blob/main/media/Technical%20Results/SD%20Skills.png
- Consulted with advisor (and searched online) to find job listing dataset sources
- Researched online which job titles are considered entry-level within GGC IT concentrations (SD and DSA)
- Downloaded datasets which likely contained job titles in the concentration researched
- Created a master spreadsheet to summarize all datasets downloaded
- Used MS Excel to explore and filter down to entry-level job titles in each dataset Made sure each dataset of job listings contained a column where the details about required skills, abilities, and responsibilities were specified by employers
- Saved dataset copies on Google Drive
- Saved a specific subset file for each dataset containing enough of one type of job title:
- For example: I created a dataset called DS-8
- Using excel I filtered titles down to just "Junior Software Developer" and save that file as "DS-8 Junior Software Developer"
- Signed up for access to Google Colab and created the Colab notebook for this project
- Created Python code that...
- Linked notebook to my Google drive
- Loaded single job title datasets (from step 7)
- Created dictionary to strip out common words during analysis
- Stripped meaningless characters out of data
- Created counter object to automatically rank top 1000 words
- Created dictionaries to home in on select words during analysis
- Created MS Excel file "SD Key Skills Python Dictionary Builder"
- Copied Top 1000 words/ranks from Python results to this file
- Worked through list to create common word and skill set dictionaries
- Formatted to put back into Python coding to build dictionaries
- Created analysis loop to filter out common words and filter down to skill words
- Created histogram plot to display skills words in a ranked order
Updates Fall 2025:
- Install Visual Studio Code
- Install Git
- Install Node.js
- 3.1: Verify installation
node -vnpm -v
- 3.1: Verify installation
- Clone the repository:
git clone https://github.com/GGC-SD/GrizzlyPaths.gitcd GrizzlyPaths/docs-Fall2025
- Install project dependencies:
- React + Vite:
npm create vite@latest my-react-app -- --template(Replace my-react-app with your desired project name) - React-router-dom:
npm install react-router-dom - Bootstrap:
npm install bootstrap@5.3.3 - Bootstrap-icon:
npm install bootstrap-icons - React-chartjs-2:
npm install react-chartjs-2 - Paraphase:
npm install papaparse - Csv-parser:
npm install csv-parser - Firebase CLI globally for deployment:
npm install -g firebase-tools - Install Firebase SDK in the project:
npm install firebase - Vitest:
npm install vitest --save-dev - Jest:
npm install jest --save-dev
- React + Vite:
- Run the project:
npm run dev
- Run the test:
npm run test
- Open up colab Notebook for project
- Click on left side arrow buttons at each step starting from the top
- Run access to Google Drive at start of each session
- For each new dataset
- Run dataset load for specific subset on Google Drive
- Run definitions for excluding common words and garbage characters
- Run long list analysis of top 1000 words
- Run definitions for focusing in on skill-set words
- Run short list analysis of specific skill-sets
- Will print lists of skill words in different orders
- Will display histogram showing top skill words in chosen order
- Log in to the website. If you don’t have an account, click the link to create one. If you have an account but you forgot your password, click the link to reset password
- In the dashboard, you can change the major by using the dropdown.
- You can click on the Recommend Course link to see 3000/4000 level courses for the each major.
- You can click on the Roadmap to see the visualize of the job posting for each major. When you click the major that you want to choose, it will show the job posting. When you click the job posting, it will show the technical skill of that job postings. Then, you can click on the technical skill to show the classes that you need to take. To change jobs, click the arrow in the bottom of the screen to reload the wheel. The wheel will then disappear and only show the majors.
- The logout is located in the upper right corner of the Dashboard.
- Datasets collected from Jan '23
- Cleaned and Analyzed for common skills and job titles
- Grizzly Path Website up to date since April '23
- Digital Media
- Enterprise Systems
- Systems and Security
- Software Development
- Data Science and Analytics
- Firebase - Log in page with full function.
- Show the general of student information in dashboard.
- There is a general list of 3000/4000 recommended courses in each major.
- Have a chart to show to top 5 jobs for each major.
- Import button for cleaned csv of merged data is in place.
- Python - value counts
- Prince module for MCA
- MCA/K-Means for classification and clustering
- Python - value_counts()
- Predicting job titles - Naive Byes, Logistic Regression, Support Vector Machine, Random Forest
- Admin authentication must be implemented in further iterations of project.
- Visualization of information can be improved if necessary.
- Page formatting needs to be improved.
- Webscraping and updating button must be added to admin box.
- Course history section that has intractability with roadmap needs to be added to student.
- Main page needs to be separated into 3 view for student, admin, and guest, so that login isn’t necessary.
- Have a continuous influx of data with live job posting data
- Create a survey for IT faculty to gather which specific skills are taught for each class - Dr. Anca can distribute
- Include full range of courses available for domains
- Incorporate more data from other popular job sites or elsewhere
- Incorporating more interactive visuals as we could not implement our PowerBI dashboard into the website due to paywall
- Improve chatbot algorithm for better matching courses with job skills
- Create/Update GGC class survey and ask collect data from students using the survey.
- Collect more information about Entriprise Systems Classes.
- Add a disclaimer page
- Refactor the TreeCreation.js file
- Create/Update GGC class survey. Needs to be user friendly and easier to extract data.
- Ask GGC IT students to complete survey
- Associate skills from job titles to GGC courses.
- Update Grizzly Path website with GGC courses