The Future of Education

Web-based learning has been promoted in education and students are required to retrieve online information to complete their assignments and study for exams [1]. Research shows that challenges exist during information retrieval, especially with novice students [2]. In this research, we aim to lessen these challenges by introducing a collaborative framework that gathers students’ searched keyphrases and analyses trends to predict the most effective subsequent keyphrase to search. The proposed solution encourages students to contribute by sharing their information retrieval trends while collectively benefiting from each other’s searching strategies. In addition, novice students will enrich their domain knowledge since the prediction results contain keyphrases searched by students from previous cohorts. Next-word prediction is a well-known area of Natural Language Processing (NLP) that is used to forecast the next word given a sentence [3] or predict trends based on time-series data [4, 5]. Word suggestions are popular in mobile devices and studies show that users rely on them while they are typing [6]. The methodology involves the implementation of a framework designed to collect online browsing activities [7]. Undergraduate students studying a BSc in Computer Science were engaged to participate in an experiment wherein they installed a Google Chrome extension capable of collecting data and predicting suitable content related to the researched domain. The collected data consisted of Uniform Resource Locators (URLs) containing keyphrases that students searched during their studies. A feature engineering process was performed to analyse and transform the data into a time-series sequence of actions and to ensure that it is fit for the intended purpose [8]. A grid-search method was employed on various machine learning models to identify the most effective hyper-parameters that can predict the next best keyphrase. The results obtained during an in-class test shows that students relying on the predictions generated by the machine learning models outperformed those who depended solely on the Internet.

Keywords: Next best action prediction, Internet activity monitoring, Hyper-parameters tuning

References:

1. Meng-Jung Tsai. Online information searching strategy inventory (oissi): A quick version and a complete version. Computers and Education, 53(2):473–483, 2009.
2. Shelda Debowski. Wrong way: Go back! an exploration of novice search behaviors while conducting an information search. The Electronic Library, 19:371–382, 12 2001.
3. Vishal Rathee and Sakshi Yede. A machine learning approach to predict the next word in a statement. In 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), pages 1604–1607. IEEE, 2023.
4. Ozge Cagcag Yolcu and Ufuk Yolcu. A novel intuitionistic fuzzy time series prediction model with cascaded structure for financial time series. Expert Systems with Applications, 215:119336, 2023.
5. Long Shi, Ruyuan Lu, Zhuofei Liu, Jiayi Yin, Ye Chen, Jun Wang, and Lu Lu. An improved robust kernel adaptive filtering method for time series prediction. IEEE Sensors Journal, 2023.
6. Florian Lehmann, Itto Kornecki, Daniel Buschek, and Anna Maria Feit. Typing behavior is about more than speed: Users’ strategies for choosing word suggestions despite slower typing rates. Pro ceedings of the ACM on Human- Computer Interaction, 7(MHCI):1–26, 2023.
7. Omar Zammit, Serengul Smith, David Windridge, and Clifford De Raffaele. Reducing the dependency of having prior domain knowledge for effective online information retrieval. Expert Systems, 40(4):e13014, 2023.
8. Johanna Walker, Elisavet Koutsiana, Joe Massey, Gefion Theurmer, and ElenaSimperl. Prompting datasets: Data discovery with conversational agents. arXiv preprint arXiv:2312.09947, 2023.