Refine
Document Type
- Master's Thesis (6)
Language
- English (6)
Has Fulltext
- yes (6)
Is part of the Bibliography
- no (6)
Institute
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.
The proliferation of online abuse on social media platforms has emerged as a significant concern, negatively impacting users' mental health and online experiences. While the Natural Language Processing (NLP) community has developed various computational methods for abuse detection, including Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs), existing approaches predominantly focus on identifying explicit forms of abuse. This narrow focus overlooks subtle and contextual forms of online harassment, which can be equally damaging to users' wellbeing.
This thesis presents a novel approach to online abuse detection by integrating contextual embeddings with sentiment analysis features through the fine-tuning of Large Language Models (LLMs). Our methodology leverages a comprehensive dataset of 47,000 annotated tweets for training, combined with sentiment analysis capabilities developed using 50,000 IMDB movie reviews. The system employs DistilBERT architecture to develop a sophisticated detection framework capable of identifying six distinct categories of abuse: ethnicity-based, age-based, gender-based, religion-based, other cyberbullying, and non-cyberbullying content. The author established a rigorous evaluation framework employing multiple metrics, including accuracy, recall, and F1 score, to assess the model's performance in detecting both explicit and nuanced forms of online abuse.
The integrated system achieved an overall accuracy of 85\% across 6 categories on the cyberbullying dataset, outperforming other methodologies applied to the same data. In direct comparison, our approach— which uniquely combines contextual embeddings with sentiment analysis—demonstrated significant improvements over traditional fine-tuning methods, such as those using only BERT or RoBERTa, particularly in detecting subtle forms of abuse. Most notably, our system was more effective at identifying passive-aggressive content and context-dependent harassment, challenges that often cause conventional detection methods to fall short. This enhanced performance can be attributed to the model's ability to capture nuanced linguistic cues through its integrated analysis of both contextual information and sentiment, thereby offering a more refined interpretation of potentially harmful content.
This research emphasizes the critical importance of incorporating subtle abuse detection into online content moderation systems. By developing more sophisticated detection methods that can identify both overt and nuanced forms of harassment, this work contributes to the creation of safer and more inclusive online spaces that facilitate constructive dialogue. The findings of this study have significant implications for the development of more effective content moderation tools and the broader goal of fostering healthier online communities.
The findings of this study demonstrate that the Random Forest (RF) algorithm provided the most accurate predictions in comparison with other boosting machine learning algorithms. Key drivers of energy consumption identified through XAI techniques such as SHAP and LIME include energy star rating, facility type, and floor area. These XAI methods helped enhance the interpretability of the models, making them more accessible for non-expert users, such as building managers and policymakers. By leveraging machine learning and XAI, this research provides a transparent and actionable framework for optimizing building energy efficiency and supporting sustainable energy management.
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.
This study examines student housing experiences in Koblenz through a mixed-methods approach that integrates surveys, geospatial analysis, and quantitative modeling to explore affordability, accessibility, satisfaction, and equity. By analyzing both objective factors—like rent, distance to campus, and travel times—and subjective measures such as satisfaction and sentiment, it identifies disparities across student groups, especially affecting international students. The findings suggest that housing outcomes stem from both structural conditions and lived experiences, revealing possible biases within the housing system. The study advocates for targeted interventions, including expanding affordable residences, enhancing transport connectivity, and promoting transparency in housing allocation to ensure equitable access in Germany’s higher education context.
This thesis tackles a common bottleneck in data-science courses: students struggle
to turn a broad interest into a focused, workable project idea. This thesis set out to
design and evaluate a compact assistant—EduIDEAtor—that makes this first mile
simpler and more intentional. The tool uses a text-first interface with plain inputs,
a small set of clearly different directions, and quick, reversible edits so students can
steer ideas without losing momentum. After building and iterating the web appli-
cation, The thesis evaluated how students experienced it and how it compared with
familiar, non-AI brainstorming. The findings are consistent: navigation and input
clarity were strong; students felt more able to generate and shape ideas; overall sat-
isfaction and willingness to continue using the tool were high. Two practical refine-
ments emerged—make back navigation clearly visible and give users finer control
over how broad or specific the suggestions are both achievable without changing
the core design. The contribution is a concrete pattern for first-mile ideation and a
set of actionable guidelines for course-level adoption.