Improving Online Experience Using Trust Adjustment Factor for Recommender Systems

© 2021 by IJCTT Journal
Volume-69 Issue-4
Year of Publication : 2021
Authors : Edwin Ouma Ngwawe, Elisha Odira Abade, Stephen Nganga Mburu
DOI :  10.14445/22312803/IJCTT-V69I4P114

How to Cite?

Edwin Ouma Ngwawe, Elisha Odira Abade, Stephen Nganga Mburu, "Improving Online Experience Using Trust Adjustment Factor for Recommender Systems," International Journal of Computer Trends and Technology, vol. 69, no. 4, pp. 83-89, 2021. Crossref,

With the improvement of computing Technologies, online shopping has become a norm to the way of life. Aggravated by the global pandemic, COVID 19, the need for social distancing has even increased the demand for online shopping as people try to stay or work at home but still run their day-to-day errands. Unscrupulous vendors have realized this sudden shift to the online market and are trying to take advantage of inexperienced shoppers by luring them using various techniques and finally ending up defrauding them or harming them physically. There exist mechanisms to help shoppers choose the right product or services, such as the use of recommender systems to help users choose a product, but the loophole again is that the recommender systems depend on historic data to make their decisions. This data can still be manipulated by unscrupulous practitioners. There is a need to take care of this loophole in the recommender system. In this study, we carried out research on what Kenyans perceive as trust; we then used the Structural Equation Modelling technique to create a parameter known as Trust adjustment factor, which we are adding to the recommender system algorithm to take care of trust issues in online shopping.

Ethics, Online fraud, Recommender systems, Structural equation modeling, Trust in online service providers.


[1] Amatriain, X., Jaimes, A., Oliver, N., & Pujol, J. M. (2011). Data Mining Methods for Recommender Systems. (F. Ricci, L. Rokach, B. Shapira, & P. B. Kantor, Eds.) New York: Springer.
[2] Best, S., & Krueger, B. (2002). New Approaches to Assessing Opinion: The Prospects for Electronic Mail Surveys. International Journal of Public Opinion Research, 4, 73-79.
[3] Gediminas, A., & Alexander, T. (2011). Context-Aware Recommender Systems. In R. Francesco, R. Lior, S. Bracha, & B. K. Paul (Eds.), Recommender Systems handbook 217-256. New York: Springer.
[4] Hox, J., & Bechger, T. (2014). An Introduction to Structural Equation Modeling. Family Science Review, 354-373.
[5] Jumia KE. (2021, March 29). Rate & Review. Retrieved from JUmia:
[6] Leskovec, J. (2003, January 1). Epinions social network. Retrieved from Stanford University:
[7] Ngwawe, E. O., Abade, E. O., & Mburu, S. N. (2020). ContextAware Computational Trust Model for Recommender Systems. EJECE, European Journal of Electrical Engineering and Computer Science, 4(6).
[8] Parasuraman, A., Zeithaml, V., & Malhotra, A. (2005). E-S-QUAL A Multiple-Item Scale For Assessing Electronic Service Quality. Journal of Service Research, 7, 213–233.
[9] Ricci, F., Rokach, L., & Shapira, B. (2011). Recommender Systems Handbook. New York: Springer.
[10] Richardson, M., Agrawal, R., & Domingos., P. (2003). Trust Management for the Semantic Web. ISWC. Retrieved from Stanford University.
[11] Roman, S. (2007). The Ethics of Online Retailing: A Scale Development and Validation from the Consumers’ Perspective. Journal of Business Ethics, 72, 131-148.
[12] Stein, C. M., Morris, N. J., & Nock, N. L. (2012). Structural Equation Modeling. Methods in molecular biology.
[13] The R Foundation. (2021, March 29). The R Project for Statistical Computing. Retrieved from R Project:
[14] Yin, C., Wang, J., & Park, J. H. (2017). An Improved Recommendation Algorithm for Big data Cloud Service based on the Trust in Sociology. Neurocomputing.