Analysis of Performance and Cognitive Differences between Traditional and Intelligent Search Interfaces and their Impact on Information Retrieval Strategies

Contemporary academic environments face an increasing challenge in selecting the most relevant and high-quality information amidst an era of information overload and rapid digital knowledge production. This is particularly evident with the widespread adoption of AI-driven smart search interfaces, which have evolved beyond neutral tools to actively influence researchers' behaviors and strategies. The problem of this study lies in the limited methodological understanding of this impact on the information behavior patterns of faculty members—specifically regarding retrieval time, cognitive effort, user satisfaction, and decision-making mechanisms within the Libyan academic context. The study employed a mixed-methods approach following an explanatory sequential design. A performance experiment was conducted where participants completed standardized research tasks using both traditional and smart interfaces. Quantitative data were gathered through a five-point Likert scale survey to measure cognitive and technical effort, ease of use, and satisfaction, alongside recording actual retrieval time. The sample consisted of (42) faculty members, supplemented by (10) interviews with experienced researchers from Libyan universities and technical institutes to interpret the quantitative findings and uncover the underlying behavioral and cognitive dimensions. The study aims to provide an integrated scientific analysis of the multi-dimensional impact of smart search interfaces on information behavior. By documenting differences through statistical measures such as mean and standard deviation, the research supports the conscious and critical use of these technologies. Ultimately, it provides a scientific foundation for designing balanced academic search interfaces that enhance research efficiency without compromising the depth of scientific exploration

Intelligent Search Interfaces , Information-Seeking Behavior , Artificial Intelligence in Academia, Cognitive Load , User Experience (UX) , Mixed Methods Research

1. Brown, Andrew, Roman, Muhammad, & Devereux, Barry. (2025). A systematic literature review of retrieval-augmented generation: Techniques, metrics, and challenges. arXiv preprint arXiv:2508.06401. [Google Scholar] [Crossref]

2. Dabengwa, Israel Mbekezeli. (2025). Are academic libraries doing enough to support the sustainable development goals (SDGs)? A mixed-methods review. Evidence Based Library and Information Practice, 20(1), 148-184. [Google Scholar] [Crossref]

3. Granikov, Vera, Hong, Quan Nha, Crist, Emily, & Pluye, Pierre. (2020). Mixed methods research in library and information science: A methodological review. Library & Information Science Research, 42(1), 101003. [Google Scholar] [Crossref]

4. Hennink, Monique, & Kaiser, Bonnie N. (2022). Sample sizes for saturation in qualitative research: A systematic review of empirical tests. Social science & medicine, 292, 114523. [Google Scholar] [Crossref]

5. Hu, Bin, Malik, Ifrah, Chen, Qiyang, Xie, Hong, Sohail, Noman, & Attar, Razaz Waheeb. (2025). Bridging Digital Literacy Gaps With AI-Driven Semantic Search Technologies. International Journal on Semantic Web and Information Systems (IJSWIS), 21(1), 1-17. [Google Scholar] [Crossref]

6. Memon, Mumtaz Ali, Ting, Hiram, Cheah, Jun-Hwa, Thurasamy, Ramayah, Chuah, Francis, & Cham, Tat Huei. (2020). Sample size for survey research: Review and recommendations. Journal of applied structural equation modeling, 4(2), i-xx. [Google Scholar] [Crossref]

7. Muhammad, Zainab Daiyab, Adamu, Rilwanu, Abubakar, Samira, & Ibrahim, Kabiru. (2025). Application of Artificial Intelligence in Information Retrieval for Academic Research: A Systematic Literature Review Using PRISMA. Dala Journal of Library and Information Practice, 3(1), 1-13. [Google Scholar] [Crossref]

8. Nguyen, Thu, Canossa, Alessandro, & Zhu, Jichen. (2024). How human-centered explainable ai interface are designed and evaluated: A systematic survey. arXiv preprint arXiv:2403.14496. [Google Scholar] [Crossref]

9. Nyimbili, Friday, & Nyimbili, Leah. (2024). Types of purposive sampling techniques with their examples and application in qualitative research studies. [Google Scholar] [Crossref]

10. Toyon, Mohammad Abu Sayed. (2021). Explanatory sequential design of mixed methods research: Phases and challenges. International Journal of Research in Business and Social Science, 10(5), 253-260. [Google Scholar] [Crossref]

11. Yang, Yuyu, Urgo, Kelsey, Arguello, Jaime, & Capra, Robert. (2025). Search+ Chat: Integrating Search and GenAI to Support Users with Learning-oriented Search Tasks. Paper presented at the Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval. [Google Scholar] [Crossref]

12. Zheng, Yue, Liu, Haiming, & Wald, Mike. (2025). A survey of Inclusive Information Access. Information Retrieval Research, 1(2), 167-196. [Google Scholar] [Crossref]

13. الشمراني*, صالح بن عبد الله. (2025). تصورات أعضاء هيئة التدريس للمهارات الناعمة اللازمة لطلبة جامعة الملك سعود في ضوء متطلبات المعرفة. مجلة الآداب للدراسات النفسية والتربوية, 7(1), 172-210. [Google Scholar] [Crossref]

14. عمر, احمد, مصطفى, الجلاب, الجلاب, محمد فتحي, عبدالمختار, & علي, أحمد محمد. (2024). سلوك البحث عن المعلومات: مراجعة علمية. مجلة الآداب والعلوم الإنسانية, [Google Scholar] [Crossref]

• Impact of AI Tools on Student Learning
• Repogent: An Autonomous Multi-Agent System for End-To-End Repository Maintenance
• Trust-Centric Federated Learning Using Blockchain-Enabled Smart Contracts: An Analysis of Data Privacy, Model Integrity, and Decentralized AI Governance
• Can AI Care? Rethinking Ethics, Clinical Integrity, and Professional Responsibility in the Digital Age of Mental Healthcare
• AI-Based Smart Irrigation System Using IoT and Machine Learning for Precision Agriculture