Using Deep Learning and Visual Analytics for Social Media Analytics to Explore Customers Relationship management for Tourism Business
|
|
Dr. Yung-Chun Chang (Associate Professor) Graduate Institute of Data Science, Taipei Medical University.
|
|
|
Dr. Chih-Hao Ku (Assistant Professor) Department of Information Systems, Cleveland State University.
|
Analyzing and extracting insights from user-generated data has become a topic of interest among businesses and research groups because such data contains valuable information, e.g., consumers’ opinions, ratings, and recommendations of products and services. However, the true value of social media data is rarely discovered due to overloaded information. Existing literature in analyzing online hotel reviews mainly focuses on a single data resource, lexicon, and analysis method and rarely provides marketing insights and decision-making information to improve business’ service and quality of products. In addition, an increasing number of customers read online consumers reviews to plan their trips and to make purchase decisions. The question of how to respond to reviews is a growing challenge for hotel managers and little is known about response strategies to negative and positive reviews. Most research has relied mostly on survey-based studies or experiments due to data unavailability. Existing studies are valuable for analyzing the online reviews and their sentiment but shed little light on analyzing the response strategies. Moreover, the computer vision and speech recognition have greatly improved with deep learning techniques during recent years; however, deep learning-based NLP is still in its infancy. To provide deeper insights into hotel online reviews and managerial responses, this project will draw on existing theories and response strategies to develop surveys and deep learning models.
In light of this, our research collaboration is to provide deeper insights into hotel online reviews and managerial responses, this project will draw on existing theories and response strategies to develop surveys and deep learning models. TMU team concentrate to develop and evaluate deep-learning models and CSU team corresponds to develop a theory-based framework and conduct visual analytics. We have different academic resources and contribute equally to the project. In the past two years, we successfully have several high-quality publications, including International Journal of Information Management, Tourism Management, Journal of Business Research, and HICSS. This research collaboration aims to address the challenges for tourism business to use smart technologies such as deep learning and visual analytics techniques as effective tools that can offer decision support information to hotel managers. Due to the novelty these topics, we expect this research project to be the foundation of this field. Moreover, the automatic analysis of social multimedia proposed in this project is a central problem in big data research that has substantial value in both academia and industry. Our results can potentially contribute to both the business and research communities as an innovative approach and breakthrough. Consequently, we can fast-track the development of AI in Taiwan. Moreover, our technologies can be transferred to domestics and international companies who have the need for social media analytics. In doing so, we can promote the position of Taiwan in global AI and big data R&D, thus increasing our competitiveness in the world as well as attract international collaboration of business and academia.