Browsing by Author "Yella Mehroze"

Now showing 1 - 2 of 2

I-Guide - A novel machine learning approach for career consultancy
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2022-11-20) Noman Khalid; FA18-BCS-215; Yella Mehroze
The project aims to provide career counselling to the intermediate students or the ones who just completed their intermediate studies. Career consultancy is usually considered a simple process where as the reality contradicts with it. To enter the world of work and selecting the professional career degrees requires a lot of effort. In this modern era, machines are replacing human work force, thereby enhancing the need for an automatic career consultancy guide. The old client-counselor relationship is getting outdated as this requires a lot of time, costing a lot of money and difficulty in finding the right an appropriate person. This project will help the ones who are struggling with the career choice in terms of their professional degree problem selection by considering their true potential, interests, financial status and a right match for their abilities. This will enable the students in particular the intermediate students to free themselves from the pressure their family put on them to select a career. This will be a guide for parents too as each and every possible attribute regarding the selection of degree program of their offspring and jobs based on their career. It will resolve the confusion of students who are stuck with multiple disciplines or subjects in their mind and cannot reach for proper counselling. This will be done by training a machine learning model on the real data of the students currently pursuing their career in hot domains at different institute. It will enable the students to check success estimates in a degree they will select based on the historic data of students of that particular field. After the successful training of machine learning model by applying algorithms, a website will be made. This website will allow the students to enter their interest, hobbies, current marks, current subject and all the similar attributes. The list of degree programs, their success estimates and a suitable university with respect to their financial status and interests will be displayed on a web portal.
Social Media Profile Tagging – A novel machine learning approach for Twitter
(Library Information Services, CUI Lahore, 2021) Saaim Siddiqui; FA18-BCS-087; Yella Mehroze
The project utilizes the sheer number of Twitter profiles and classifies them based on profuse facets. Dominant aspects have been extracted from the users of Twitter that are discernible on a profile such as the number of followers, username, retweets count, and likes count, etc. The proposed system categorizes Twitter profiles into six categories: Political, Actor, Sports, Singer, Educational, and Content Creator. A machine learning approach has been used in the proposed model that works on these abundant features. Several heterogeneous models such as Bayesian networks, SVC, Random Forest, and CNN are used in the study to achieve desirable results. The preferred system is applicable to all Twitter profiles and helps label them through profile URLs. It also helps recommender systems and Twitter to analyze the profiles based on broader categories