TravelBot: Utilizing social media dialogue for Travel Recommendation
Author(s):
Nandarani Kadam, Sarika Solanke
Keywords:
Artificial Intelligence, Chatbot, Machine
Learning, Natural language processing, Travel, Twitter.
Abstract
Use of social media in tourism is increasing rapidly. Due to increasing Internet usage, many businesses now use online platforms to handle customer inquiries, and many of them turn to chatbots for improving their customer service. Travelbot is a chatbot; a computer application that interacts with users using natural language in a similar way to imitate a human travel agent. Travelbot is using twitter data for recommending countries to users for travel. The travelbot uses tweepy api and perform filtering on data to get all travel related tweets. When travelbot recommended countries to travel realized that there are number of features available like safety, quality of life, healthcare etc. So all these features are important? To solve this question need to use classification algorithm. First Decision tree algorithm is used with these datasets, on the values of feature importance got accuracy score 48.39%. Then Random Forest Algorithm is used with these datasets, on the values of feature importance got accuracy score 78.65%. According to these values we can see the accuracy of random forest is increased 30% as compare to decision tree algorithm.
Article Details
Unique Paper ID: 152160
Publication Volume & Issue: Volume 8, Issue 2
Page(s): 563 - 568
Article Preview & Download
Share This Article
Conference Alert
NCSST-2021
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2021
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT