Text classification in tourism and hospitality – a deep learning perspective

Abstract

Purpose This study aims to investigate the current state of research using deep learning methods for text classification in the tourism and hospitality field and to propose specific guidelines for future research. Design/methodology/approach This study undertakes a qualitative and critical review of studies that use deep learning methods for text classification in research fields of tourism and hospitality and computer science. The data was collected from the Web of Science database and included studies published until February 2022. Findings Findings show that current research has mainly focused on text feature classification, text rating classification and text sentiment classification. Most of the deep learning methods used are relatively old, proposed in the 20th century, including feed-forward neural networks and artificial neural networks, among others. Deep learning algorithms proposed in recent years in the field of computer science with better classification performance have not been introduced to tourism and hospitality for large-scale dissemination and use. In addition, most of the data the studies used were from publicly available rating data sets; only two studies manually annotated data collected from online tourism websites. Practical implications The applications of deep learning algorithms and data in the tourism and hospitality field are discussed, laying the foundation for future text mining research. The findings also hold implications for managers regarding the use of deep learning in tourism and hospitality. Researchers and practitioners can use methodological frameworks and recommendations proposed in this study to perform more effective classifications such as for quality assessment or service feature extraction purposes. Originality/value The paper provides an integrative review of research in text classification using deep learning methods in the tourism and hospitality field, points out newer deep learning methods that are suitable for classification and identifies how to develop different annotated data sets applicable to the field. Furthermore, foundations and directions for future text classification research are set.

Artificial intelligence research in hospitality: a state-of-the-art review and future directions

“…Moreover, this study found that sophisticated neural networks and deep learning algorithms, such as convolution neural networks (CNNs) and long short-term memory (LSTM) models, were on the rise in AI methods research during the study period. These advanced neural network algorithms were used mostly for classification and prediction, given their ability to handle complex data and their high accuracy (Liu et al , 2023). In line with Doborjeh et al (2022), this study found that these advanced AI-based models were most frequently adopted in research on demand forecasting.…”

“…First, AIGCs, such as AI-generated editorials, graphics and videos, could be a new type of data source in AI methods research. Second, hospitality researchers could leverage the co-pilot of generative AI applications to augment their coding skills in data collection and analysis (Liu et al , 2023). Albeit with assistance of these tools, researchers still need to improve their capability in searching for valuable research questions, selecting appropriate research method and algorithms and properly applying and communicating this knowledge in their research to publish in top hospitality journals.…”

A novel deep learning method to use feature complementarity for review helpfulness prediction

“…The DL technique must be applied to extract significant information on various features that affect review helpfulness. The hospitality and tourism industries have widely applied the DL technique, which offers numerous advantages (Essien and Chukwukelu, 2022; Liu et al , 2023). First, unlike the traditional ML approach, the DL technique is a data-driven approach that does not rely on assumptions regarding the data.…”

Analisis Sentimen Evaluasi Reaksi E-Learning Menggunakan Algorima Naïve Bayes, Support Vector Machine Dan Deep Learning

“…Berdasarkan studi literatur yang dilakukan [23], secara umum teknik machine learning yang banyak digunakan pada penelitian analisis sentimen atau opinion mining adalah Naïve Bayes (NB), support vector machine (SVM), dan neural network (NN) karena memiliki performa yang baik. Di samping itu, algoritma Deep Learning (DL) sebagai variasi bentuk neural network dengan lapisan yang lebih banyak turut mengalami peningkatan popularitas penggunaan pada penelitian analisis sentimen [23], [24]. Penelitian yang dilakukan [25] menggunakan algoritma NB, SVM dan Random Forest (RF) untuk klasifikasi sentimen review destinasi wisata menyimpulkan algoritma SVM memiliki tingkat akurasi lebih baik yaitu 67,97% dibandingkan algoritma NB (61,33%) dan RF (63,55%).…”