Categorizing Natural Language-Based Customer Satisfaction: An Implementation Method Using Support Vector Machine and Long Short-Term Memory Neural Network

Abstract

Analyzing natural language-based Customer Satisfaction (CS) is a tedious process. This issue is practically true if one is to manually categorize large datasets. Fortunately, the advent of supervised machine learning techniques has paved the way toward the design of efficient categorization systems used for CS. This paper presents the feasibility of designing a text categorization model using two popular and robust algorithms – the Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) Neural Network, in order to automatically categorize complaints, suggestions, feedbacks, and commendations. The study found that, in terms of training accuracy, SVM has best rating of 98.63% while LSTM has best rating of 99.32%. Such results mean that both SVM and LSTM algorithms are at par with each other in terms of training accuracy, but SVM is significantly faster than LSTM by approximately 35.47s. The training performance results of both algorithms are attributed on the limitations of the dataset size, high-dimensionality of both English and Tagalog languages, and applicability of the feature engineering techniques used. Interestingly, based on the results of actual implementation, both algorithms are found to be 100% effective in accurately predicting the correct CS categories. Hence, the extent of preference between the two algorithms boils down on the available dataset and the skill in optimizing these algorithms through feature engineering techniques and in implementing them toward actual text categorization applications.

Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method

“…e piano score notes of the music are transcribed. Corpuz [9] proposed the Harmonic Pitch Class Profile (HPCP) feature and used it in the piano score recognition system.…”

“…The piano score notes of the music are transcribed. Corpuz [ 9 ] proposed the Harmonic Pitch Class Profile (HPCP) feature and used it in the piano score recognition system. The experimental results show that the HPCP feature can effectively reduce the influence of the type of instrument on the notes of the piano score.…”

Can Artificial Intelligence be Used to Improve Productivity by Automating Elements of the User Experience Design Processes?<b> </b>

“…The malleable nature of LSTM benefits our research immensely. Other authors have explored LSTM use in design classification models (Corpuz 2021) to learn text patterns and classify customer complaints, feedback, and commendations.…”

Exploration on the Application Path of College English MOOCS Teaching under the Background of Internet of Things

“…Holme et al analyze whether these resources meet the actual needs of English teachers by investigating and comparing teachers' use of information technology [ 11 ]. Hong et al have changed the difficulties of traditional teaching methods in students' learning of microbiology and adopted a variety of modern multimedia teaching methods to ensure the teaching quality [ 12 ] and proposed the collaborative role of computer support and encouraged teachers to actively integrate MOOCs into the improvement of the teaching path [ 13 ].…”

“…Corpuz et al introduce the feasibility of designing a text classification model using two popular and robust algorithms: support vector machine (SVM) and long-term and short-term memory (LSTM), which are used to automatically classify complaints, suggestions, feedback, and praise. The degree of preference between the two algorithms can be attributed to the available data sets and the skills of optimizing these algorithms through feature engineering technology and applying them to practical text classification applications [ 13 ]. Hong et al provided customer evaluation data by analyzing the correlation between airline customer satisfaction based on customer evaluation data.…”