Smart Chatbot to Assist Users of Employment Websites in Job Search, Skill Development, and Networking Opportunities

Abstract

This paper presents the development and implementation of a smart chatbot designed to assist users of employment websites in various aspects of their job search, skill development, and networking endeavors built using bert model, spacy model and large language model. With the increasing reliance on online platforms for job hunting and career advancement, there is a growing need for intelligent tools that can streamline the process and provide personalized support to users. This article examines a chatbot that provides many functionalities to improve job search outcomes and user experience. These functionalities include personalized job recommendations, skill development suggestions, and networking opportunities tailored to the user\'s queries. The paper outlines the methodology used in the development of the chatbot, including the integration of natural language processing techniques and machine learning models. The paper presents findings from comprehensive evaluation, shedding light on the efficacy of the chatbot\'s functionalities. The implications of this research extend to both academia and industry, underscoring the potential of AI-driven chatbots to revolutionize the way individuals navigate the job market and pursue career advancement opportunities.

Introduction

I. INTRODUCTION

In today’s digital age, job search websites have become essential resources for people looking for chances for professional growth, networking, and employment. Numerous job ads, tools for improving skills, and channels for interacting with peers and possible employers are all provided by these sites. But for certain users, especially those who encounter obstacles like information overload, inadequate personalisation, and a lack of customised advice, efficiently browsing these websites can be difficult. The efficiency and ease offered by current technology are frequently lacking in traditional techniques of career growth and job seeking. Consequently, in order to improve user experience and maximise employment domain outcomes, creative solutions utilising chatbot and artificial intelligence (AI) technologies like large language Models are clearly needed. One way to address various important demands and potential in the sector is to construct a smart chatbot specifically designed to help users of employment websites. A chatbot of this kind can provide users with individualised assistance and support during their job search by utilising artificial intelligence and natural language processing. This include recommending appropriate jobs based on the user's tastes and qualifications, making customised recommendations for programmes that would help them grow their skills and get trained, and helping them network with other industry professionals. Furthermore, a sophisticated chatbot can facilitate users' interactions with employment websites, guide them through the difficulties of the job search process, and eventually improve their chances of discovering options for suitable employment.  The primary objectives of this research are to leverage advanced AI technologies, including the BERT model, SpaCy, and large language models, to design and develop a smart chatbot tailored to assist users of employment websites comprehensively. Harnessing the power of these cutting-edge technologies, the chatbot aims to provide personalized recommendations and assistance based on users' queries, suggesting relevant skill development resources, and facilitating networking opportunities with professionals in their respective fields.

II. LITERATURE SURVEY

The research by Dillahunt and etal [1] examined the manner in which individuals seek employment in the current digital era. They discovered that exploring job websites and other online job boards is a really beneficial way to find employment. They did, however, also find that networking—whether through friends or business contacts—remains crucial to employment prospects.

It's fascinating to note how these tactics vary in their effectiveness for various demographic groups based on factors such as education level or age. In summary, this study provides valuable insights into the evolution of the job search process and the reasons why it is critical to assist all job seekers in the contemporary labour market.

The creation, analysis, and assessment of chatbots customised for career advancement and job search support have been thoroughly studied in the past by Koivunen and etal [2] . The purpose of these chatbots is to assist users with job listings and application procedures, comprehend user inquiries, and offer tailored recommendations. By responding to questions, making pertinent recommendations, and setting up meetings with possible employers, they provide job searchers with prompt support. Nevertheless, issues with data security and privacy still need to be addressed, as does guaranteeing the precision and dependability of chatbot responses. To fully investigate how chatbots might improve the hiring process and help users reach their career objectives, more study is required.

The development of chatbots for employment websites relies on advancements in AI technologies and NLP techniques. Devlin and etal. [3] have extensively worked on how BERT can be used for language understanding. Honnibal and et al. [4] did research on spacy for entity recognition. Zhao and etal in [5] have explored various large language models and their use cases. These technologies enable chatbots to understand user queries and provide relevant responses, facilitating effective assistance for job seekers navigating employment websites.

III. METHODOLOGY

The whole methodology is categorised into the below steps: i.e

1. Data collection: collecting different types of queries (data) from various sources and labelling them with the probable intents
2. Annotating the collected queries with entities for entity recognition.
3. Training the Bert model on labelled queries for intent classification.
4. Training the spacy model for custom-named entity recognition.
5. Having a knowledge base that has a repository of different types of jobs.
6. Having a Large Language Model for Skill Development Suggestions.
7. Integrating all of the above with a user interface where users can enter queries and get recommendations

A. Data Collection

Data was collected from various sources on the web, and textual expansion was done on those queries by changing the location and job type, resulting in an increase in the size of the data to 1339 queries. The figure in [1] demonstrates the same. All 1339 queries were labelled based on their nature and probable intent.

Conclusion

This study demonstrates the potential of leveraging advanced AI technologies, including the BERT model, SpaCy, and GPT-3.5, to develop a smart chatbot aimed at assisting users of employment websites in their job search, skill development, and networking endeavors. Smart chatbots can offer personalized recommendation & guidance to job seekers at every stage of their job search journey. The findings of this research Manifest the effectiveness of chatbot in enhancing the job search experience for users. This research lays foundation for future innovations in chatbot design and implementation. Moving forward, with more data coming in the performance and the generalization ability of the models will only get better resulting in, tackling users query in a more better way.

References

[1] Dillahunt, Tawanna R., et al. \"Examining the use of online platforms for employment: A survey of US job seekers.\" Proceedings of the 2021 CHI conference on human factors in computing Systems. 2021. [2] Koivunen, Sami, et al. \"The march of Chatbots into recruitment: recruiters’ experiences, expectations, and design opportunities.\" Computer Supported Cooperative Work (CSCW) 31.3 (2022): 487-516. [3] Devlin, Jacob, et al. \"Bert: Pre-training of deep bidirectional transformers for language understanding.\" arXiv preprint arXiv:1810.04805 (2018). [4] Honnibal, Matthew, et al. \"spaCy: Industrial-strength natural language processing in python.\" (2020). [5] Zhao, Wayne Xin, et al. \"A survey of large language models.\" arXiv preprint arXiv:2303.18223 (2023). [6] Chen, Qian, Zhu Zhuo, and Wen Wang. \"Bert for joint intent classification and slot filling.\" arXiv preprint arXiv:1902.10909 (2019). [7] Shelar, Hemlata, et al. \"Named entity recognition approaches and their comparison for custom ner model.\" Science & Technology Libraries 39.3 (2020): 324-337. [8] Banker, Kyle, et al. MongoDB in action: covers MongoDB version 3.0. Simon and Schuster, 2016. [9] Paparrizos, Ioannis, B. Barla Cambazoglu, and Aristides Gionis. \"Machine learned job recommendation.\" Proceedings of the fifth ACM Conference on Recommender Systems. 2011. [10] Clavié, Benjamin, et al. \"Large language models in the workplace: A case study on prompt engineering for job type classification.\" International Conference on Applications of Natural Language to Information Systems. Cham: Springer Nature Switzerland, 2023.s

Copyright

Copyright © 2024 Kala Kushal Jain, P. Sravanthi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.