In this era of the information age, a major number of people spend their time on social networking sites. Among different social networking sites, Facebook is one of the most popular due to its accessibility and many other reasons. Nowadays, people use Facebook not only for general purposes but also for business purposes as it provides free opportunity to promote products and services. Users of the products or services share their opinion and feedback on the Facebook page. The amount of the users’ data regarding the opinion and feedback is huge. This is very essential to analyze this vast amount of data and extract knowledge from it. For business owners, it is important to consider their clients’ sentiments as proper analysis of customers’ feedback helps them to take better future planning. In this research work, we proposed a noble strategy to predict users’ sentiments from their Facebook comments on online food delivery services. To accomplish this research work, we have mainly considered the BERT machine learning technique. To understand the performance of the BERT in this context, we have applied Char-CNN, Graph-CNN, LSTM, and Bi-LSTM machine learning techniques also. Lastly, the obtained result of the BERT is compared with other four applied techniques in terms of performance evaluation techniques. It is found that BERT outperforms the other applied techniques with achieving the accuracy of 92.86%.