The complex process by which humans use their senses to clarify and understand the world around them is referred to as human perception. Analyzing human perception is important for comprehension of how humans think, feel, and act, which is helpful in a variety of contexts and ultimately promotes improved understanding, communication, and engagement. This study examines the field of text mining-based human perception analysis using a precisely chosen dataset of Twitter customer service discussions. Decision Trees, KNN, Naive Bayes, and GLM are four different algorithms that are methodically examined to determine which is the most effective method for understanding and predicting human perception from textual data. After an exhaustive analysis, the Decision Tree algorithm is shown to be the best performer, closely followed by Naive Bayes. The human perception analysis of text mining, including the methodology, findings, and implications, is described in depth.