ABSTRACT
Nowadays, all kinds of service-based organizations open online feedback possibilities for customers to share their opinion. Swiss National Railways (SBB) uses Facebook to collect commuters' feedback and opinions. These customer feedbacks are highly valuable to make public transportation option more robust and gain trust of the customer. The objective of this study was to find interesting association rules about SBB's commuters pain points. We extracted the publicly available FB visitor comments and applied manual text mining by building categories and subcategories on the extracted data. We then applied Apriori algorithm and built multiple frequent item sets satisfying the minsup criteria. Interesting association rules were found. These rules have shown that late trains during rush hours, deleted but not replaced connections on the timetable due to SBB's timetable optimization, inflexibility of fines due to unsuccessful ticket purchase, led to highly customer discontent. Additionally, a considerable amount of dissatisfaction was related to the policy of SBB during the initial lockdown of the Covid-19 pandemic. Commuters were often complaining about lack of efficient and effective measurements from SBB when other passengers were not following Covid-19 rules like public distancing and were not wearing protective masks. Such rules are extremely useful for SBB to better adjust its service and to be better prepared by future pandemics. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.