Refine
Document Type
- Master's Thesis (3)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Institute
Along with the increased use of automation processes in every other task, job recommendations as well as hiring have also become partially automated. In the process of applying only to those jobs that are recommended by a system or choosing only from those candidates that are selected by an automated system, it becomes highly important to find out if the automated systems are trustworthy enough to provide fair decisions. There has been research on fairness in this sector, where the main focus has been on a single protected attribute, in most cases ’gender.’ That is why the aim of this research is to delve deeper into a deep learning transformer-based algorithm used for job matching with a text-based resume dataset containing several demographic attributes to investigate the fairness of the algorithm not only for gender but also for other demographic groups such as race, age group, and experience level. The fairness evaluation has been carried out using multiple fairness metrics, including demographic parity, conditional demographic parity, and equal opportunity. The transformer models that are pretrained language models are chosen for this study due to their ability to understand the meaning and context of words in resumes and job descriptions. The thesis further investigates bias using an alternative approach by working on a dataset containing varying protected attributes and then conducting a comparable analysis of several bias mitigation methods, including multiple layers of data resampling, along with sensitivity testing through data modification in the preprocessing step of the recommendation process. The research reveals that a system performing fairly when considering a single protected attribute can even hide intersectional unfairness and that the bias mitigation methods do not ensure a balanced improvement across each subgroup when considering multiple combinational demographic groups.
Enhancing AI Telephony System with
Large Language Models: A Comparative
Study on ’Telegra KIT’
(2025)
Nowadays, artificial intelligence (AI) has been widely used in telephony systems. It
allows telephony systems to automate customer interactions without any human in-
tervention. However, traditional approaches used across various tasks in telephony
systems has some limitations. To address these limitations, this thesis investigates
the potential of Large Language Models (LLMs) to enhance AI-driven telephony
systems by improving intent recognition, entity extraction, inquiry question gener-
ation, and synthetic training data creation.
We have conducted a comparative study to evaluate the performance of LLM-
based methods and traditional methods across above mentioned tasks. This study
is conducted on Telegra-KIT, an AI-based telephony platform. We have used real-
world data of Telegra-KIT to assess the performance. The results show that LLMs
outperformed traditional approaches by improving intent recognition accuracy from
18.42% to 39.71% and entity extraction accuracy from 52.69% to 82.21%. LLM-based
approach was also able to create effective inquiry questions when a caller’s intent is
uncertain. The results also demonstrated the ability of LLM to create high-quality
synthetic training data to address data scarcity issues and enhance model general-
ization.
The findings of this thesis contribute to the advancement of AI telephony sys-
tems by offering a more context-aware, adaptable approach for important tasks in
telephony.
Exploring Academic Perspectives: Sentiments and Discourse on ChatGPT Adoption in Higher Education
(2024)
Artificial intelligence (AI) is becoming more widely used in a number of industries, including in the field of education. Applications of artificial intelligence (AI) are becoming crucial for schools and universities, whether for automated evaluation, smart educational systems, individualized learning, or staff support. ChatGPT, anAI-based chatbot, offers coherent and helpful replies based on analyzing large volumes of data. Integrating ChatGPT, a sophisticated Natural Language Processing (NLP) tool developed by OpenAI, into higher education has sparked significant interest and debate. Since the technology is already adapted by many students and teachers, this study delves into analyzing the sentiments expressed on university websites regarding ChatGPT integration into education by creating a comprehensive sentiment analysis framework using Hierarchical Residual RSigELU Attention Network (HR-RAN). The proposed framework addresses several challenges in sentiment analysis, such as capturing fine-grained sentiment nuances, including contextual information, and handling complex language expressions in university review data. The methodology involves several steps, including data collection from various educational websites, blogs, and news platforms. The data is preprocessed to handle emoticons, URLs, and tags and then, detect and remove sarcastic text using the eXtreme Learning Hyperband Network (XLHN). Sentences are then grouped based on similarity and topics are modeled using the Non-negative Term-Document Matrix Factorization (NTDMF) approach. Features, such as lexico-semantic, lexico structural, and numerical features are extracted. Dependency parsing and coreference resolution are performed to analyze grammatical structures and understand semantic relationships. Word embedding uses the Word2Vec model to capture semantic relationships between words. The preprocessed text and extracted features are inputted into the HR-RAN classifier to categorize sentiments as positive, negative, or neutral. The sentiment analysis results indicate that 74.8% of the sentiments towards ChatGPT in higher education are neutral, 21.5% are positive, and only 3.7% are negative. This suggests a predominant neutrality among users, with a significant portion expressing positive views and a very small percentage holding negative opinions. Additionally, the analysis reveals regional variations, with Canada showing the highest number of sentiments, predominantly neutral, followed by Germany, the UK, and the USA. The sentiment analysis results are evaluated based on various metrics, such as accuracy, precision, recall, F-measure, and specificity. Results indicate that the proposed framework outperforms conventional sentiment analysis models. The HR-RAN technique achieved a precision of 98.98%, recall of 99.23%, F-measure of 99.10%, accuracy of 98.88%, and specificity of 98.31%. Additionally, word clouds are generated to visually represent the most common terms within positive, neutral, and negative sentiments, providing a clear and immediate understanding of the key themes in the data. These findings can inform educators, administrators, and developers about the benefits and challenges of integrating ChatGPT into educational
settings, guiding improvements in educational practices and AI tool development.