Where can my career take me?: harnessing dialogue for interactive career goal recommendations
summary
An interactive career recommender is built as a chatbot that extracts maximal sequential patterns from job-transition networks, scores candidate jobs by pattern match, proficiency and a dialog-driven preference score, and shows that pattern-only signals beat classic popularity and collaborative filters. Evaluation on two real datasets predicts long-term targets better than baselines, and simulated users requiring on average 6 turns with no feedback versus 2.2 turns average when seniority is provided. The system is explainable and ready for user studies.
AI-written summary · about
chapters (6)
- 0:00Start
- 4:21Scoring Function
- 5:05Proficiency Score
- 5:16Preference Score
- 7:31Measure the Performance of the System
- 15:27Strategies for Providing Feedback Regarding Related to Skill
related talks
22mAll Work and No Play? Conversations with a Question-and-Answer Chatbot in the Wild
19mThe new age of HR: Leveraging AI for a high-tech & high-touch experience
10mCritiquing for Music Exploration in Conversational Recommender Systems
13mInterQuest: A Mixed-Initiative Framework for Dynamic User Interest Modeling in Conversational Search
13mOnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language ...
25mEnhancing Job Matching With Knowledge Graphs and RAG
17mUnlocking the Future of HR Tech
25mConversational AI