In the current digital era, the proliferation of online content has overwhelmed users with vast amounts of information, necessitating effective filtering mechanisms. Recommender systems have become indispensable in addressing this challenge, tailoring content to individual preferences and significantly enhancing user experience. This paper delves into the latest advancements in recommender systems, analyzing 115 research papers and 10 articles, and dissecting their application across various domains such as e-commerce, entertainment, and social media. We categorize these systems into content-based, collaborative, and hybrid approaches, scrutinizing their methodologies and performance. Despite their transformative impact, recommender systems grapple with persistent issues like scalability, cold-start problems, and data sparsity. Our comprehensive review not only maps the current landscape of recommender system research but also identifies critical gaps and future directions. By offering a detailed analysis of datasets, simulation platforms, and evaluation metrics, we provide a robust foundation for developing next-generation recommender systems poised to deliver more accurate, efficient, and personalized user experiences, inspiring innovative solutions to drive forward the evolution of recommender technology.
Category: Sreyoshi Bhaduri, Ph.D.
Sreyoshi Bhaduri, Ph.D.
Biography
Linkedin
Google Scholar
-
Qualitative Insights Tool (QualIT): LLM Enhanced Topic Modeling
Topic modeling is a widely used technique for uncovering thematic structures from large text corpora. However, most topic modeling approaches e.g. Latent Dirichlet Allocation (LDA) struggle to capture nuanced semantics and contextual understanding required to accurately model complex narratives. Recent advancements in this area include methods like BERTopic, which have demonstrated significantly improved topic coherence and thus established a new standard for benchmarking. In this paper, we present a novel approach, the Qualitative Insights Tool (QualIT) that integrates large language models (LLMs) with existing clustering-based topic modeling approaches. Our method leverages the deep contextual understanding and powerful language generation capabilities of LLMs to enrich the topic modeling process using clustering. We evaluate our approach on a large corpus of news articles and demonstrate substantial improvements in topic coherence and topic diversity compared to baseline topic modeling techniques. On the 20 ground-truth topics, our method shows 70% topic coherence (vs 65% & 57% benchmarks) and 95.5% topic diversity (vs 85% & 72% benchmarks). Our findings suggest that the integration of LLMs can unlock new opportunities for topic modeling of dynamic and complex text data, as is common in talent management research contexts.
-
Path to Personalization: A Systematic Review of GenAI in Engineering Education
This systematic review paper provides a comprehensive synthesis across 162 articles on Generative Artificial Intelligence (GenAI) in engineering education (EE), making two specific contributions to advance research in the space. First, we develop a taxonomy that categorizes the current research landscape, identifying key areas such as Coding or Writing Assistance, Design Methodology, and Personalization. Second, we highlight significant gaps and opportunities, such as lack of customer-centricity and need for increased transparency in future research, paving the way for increased personalization in GenAI-augmented engineering education. There are indications of widening lines of enquiry, for example into human-AI collaborations and multidisciplinary learning. We conclude that there are opportunities to enrich engineering epistemology and
competencies with the use of GenAI tools for educators and students, as well as a need for further research into best and novel practices. Our discussion serves as a roadmap for researchers and educators, guiding the development of GenAI applications that will continue to transform the engineering education landscape, in classrooms and the workforce. -
Reconciling methodological paradigms: Employing large language models as novice qualitative research assistants in talent management research
Qualitative data collection and analysis approaches, such as those employing interviews and focus groups, provide rich insights into customer attitudes, sentiment, and behavior. However, manually analyzing qualitative data requires extensive time and effort to identify relevant topics and thematic insights. This study proposes a novel approach to address this challenge by leveraging Retrieval Augmented Generation (RAG) based Large Language Models (LLMs) for analyzing interview transcripts. The novelty of this work lies in strategizing the research inquiry as one that is augmented by an LLM that serves as a novice research assistant. This research explores the mental model of LLMs to serve as novice qualitative research assistants for researchers in the talent management space. A RAG-based LLM approach is extended to enable topic modeling of semi-structured interview data, showcasing the versatility of these models beyond their traditional use in information retrieval and search. Our findings demonstrate that the LLM-augmented RAG approach can successfully extract topics of interest, with significant coverage compared to manually generated topics from the same dataset. This establishes the viability of employing LLMs as novice qualitative research assistants. Additionally, the study recommends that researchers leveraging such models lean heavily on quality criteria used in traditional qualitative research to ensure rigor and trustworthiness of their approach. Finally, the paper presents key recommendations for industry practitioners seeking to reconcile the use of LLMs with established qualitative research paradigms, providing a roadmap for the effective integration of these powerful, albeit novice, AI tools in the analysis of qualitative datasets within talent
-
Investigating Transition Phases: An Autoethnographic Study of International Women of Color Engineering Educators in the US
The study aims to explore the transitions experienced by international Women of Color (IWoC) engineers in the US as they navigate their academic and professional lives. Motivated by the lack of research on IWoC’s experiences, specifically around transition points of their lives, four international Women of Color participated in this qualitative auto-ethnographic deep-dive. All four researchers have attended college in the United States for their high educational degrees focused on education/engineering education and are currently involved in engineering education scholarship work.
-
Outsiders: Pathways and Perspectives from Engineering Education PhDs Outside Academia
This article presents a critical exploration and recommendation based on the lived experiences of PhD graduates in Engineering Education who have ventured into non-academic career paths. The work is rooted in an auto-ethnographic research approach, and the report aims to mimic a live virtual panel. It seeks to elucidate the experiences and challenges faced by PhD graduates who diverged from traditional academic roles to pursue careers in industry, entrepreneurship, consulting, and pre-college leadership. These narratives reveal a complex landscape of motivations, perceived hierarchical barriers, and under-recognition within academic and non-academic sectors, highlighting a divide between industry and academia. The paper delves into the unique challenges faced by non-academic engineering educators, such as confronting a culture that often questions their value outside traditional faculty roles and the overarching perception that non-research roles are less significant. Despite these challenges, the authors argue for the vital role these professionals play in bridging the gap between research, instruction, and practical application in engineering education. They emphasize the importance of ASEE or similar professional societies in recognizing and leveraging the diverse contributions of non-academic engineering educators to foster a more inclusive and supportive community. Key takeaways and recommendations include the necessity for ASEE and similar bodies to shift normative expectations, create inclusive and equitable environments, and actively value diverse career trajectories. The paper calls for actionable strategies to build more inclusive professional communities, create safe spaces for discussing career diversity, and establish stronger connections between current students and diverse alums. The overarching goal is to cultivate an environment where all forms of contribution to engineering education are valued, encouraging a broader spectrum of career considerations among graduates and professionals. The authors seek not only to share insights but also to galvanize a nascent community of like-minded engineering educators aspiring or working outside the traditional academic sphere.
-
(Multi-disciplinary) Teamwork makes the (real) dream work: Pragmatic recommendations from industry for engineering classrooms
Many students choose to major in engineering to join the community of professional engineers and gain exposure to the field through their college experience. However, research suggests that engineering graduates may not be adequately prepared for the workplace due to the complexities of engineering work. Engineering work involves complexity, ambiguity, and contradictions, and developing innovation skills requires analyzing real-world problems that are often ill-defined and multifaceted. Therefore, it is essential for engineering students to have opportunities to work in multi-disciplinary teams to develop their skills in problem-solving and innovation. This emphasis on the need for exposure to multi-disciplinary problem solving holds true not only for undergraduate engineers in training, but also for graduate students focused on engineering education.
This paper draws from experiences of a multi-disciplinary team (including engineers, scientists, UX researchers, Industrial-Organization (I-O) psychologists, economists, and program and product managers) studying talent management in the tech industry, to present lessons learned from leading with science to understand, inform, and improve employee experiences at a large private technology company. Our paper exemplifies how projects in industry leverage multi-disciplinary expertise and presents recommendations for new graduates and engineering professionals. Ultimately, this paper affords an opportunity for educators to expand on examples of how multiple disciplines come together to study engineers in the workforce.
-
Beyond the algorithm: Empowering ai practitioners through liberal education
As AI technology continues to transform society, there is a growing need for engineers and technologists to develop interdisciplinary skills to address complex, society-wide problems. However, there is a gap in understanding how to effectively design and deliver inter-disciplinary education programs for AI-related training. This paper addresses this gap by reporting on a successful summer school program that brought together specialists from around the world to engage in deliberations on responsible AI, as part of a Summer School in Responsible AI led by Mila – Quebec Artificial Intelligence Institute. Through deep dive auto-ethnographic reflections from five individuals, who were either organizers or participants, augmented with end-of-program feedback, we provide a rich description of the program’s planning, activities, and impact. Specifically, our study draws from engineering education research, bridging the gap between research and practice to answer three research questions related to the program: (1) How did the program design enable a more effective understanding of interdisciplinary problem-sets? (2) How did participants experience the interdisciplinary work of the program? (3) Did the program affect participants’ impact on interdisciplinary problem-sets after the program? Our findings highlight the benefits of interdisciplinary, holistic, and hands-on approaches to AI education and provide insights for fellow engineering education researchers on how to design effective programs in this field.
-
Reimagining AI Conference Mission Statements to Promote Inclusion in the Emerging Institutional Field of AI
AI conferences play a crucial role in education by providing a platform for knowledge sharing, networking, and collaboration, shaping the future of AI research and applications, and informing curricula and teaching practices. This work-in-progress, innovative practice paper presents preliminary findings from textual analysis of mission statements from select artificial intelligence (AI) conferences to uncover information gaps and opportunities that hinder inclusivity and accessibility in the emerging institutional field of AI. By examining language and focus, we identify potential barriers to entry for individuals interested in the AI domain, including educators, researchers, practitioners, and students from underrepresented groups. Our paper employs the use of the Language as Symbolic Action (LSA) framework [1] to reveal information gaps in areas such as no explicit emphasis on DEI, undefined promises of business and personal empowerment and power, and occasional elitism. These preliminary findings uncover opportunities for improvement, including the need for more inclusive language, an explicit commitment to diversity, equity, and inclusion (DEI) initiatives, clearer communications about conference goals and expectations, and emphasis on strategies to address power imbalances and promote equal opportunities for participation. The impact of our work is bi-fold: 1) we demonstrate preliminary results from using the Language as Symbolic Action framework to text-analysis of mission statements, and 2) our preliminary findings will be valuable to the education community in understanding gaps in current AI conferences and consequently, outreach. Our work is thus of practical use for conference organizers, engineering and CS educators and other AI-related domains, researchers, and the broader AI community. Our paper highlights the need for more intentional and inclusive conference design to foster a diverse and vibrant community and community of AI professionals.
-
Bridging the Gap: Exploring Semiconductors Exposure and Motivation among Multidisciplinary Engineering Students
Several educational initiatives are currently underway to address workforce challenges in the semiconductors industry. Assessing students’ exposure to and motivation for semiconductors-related topics is an essential initial step toward recognizing areas where primary efforts should be concentrated. The primary objective of this study is to assess students’ awareness and motivation concerning semiconductors in the context of a multidisciplinary introduction to electrical engineering course. Through quantitative analysis and the administration of an existing validated survey instrument, we aim to explore students’ exposure to semiconductors-related topics and potential correlations between awareness, motivation, and demographic variables, including gender and class standing. The instrument was administered to a cohort of 255 students enrolled in a multidisciplinary course covering the fundamentals of electrical engineering. Preliminary data indicates that only 9% of the students in this cohort haven taken a class about semiconductors and only 3% have some interest in pursuing a career in the semiconductors field. The results of this analysis hold several significant implications for engineering education and the semiconductor industry. Firstly, the limited exposure to and interest in semiconductors among engineering students suggest the need for curriculum alignment with the demands of the semiconductor industry and interdisciplinary education. By doing so, we empower students from diverse disciplines to contribute to technological advancements, innovation, and problem-solving fostering a more inclusive, diverse, and well-rounded workforce within the semiconductor sector.