Abstract
When making a travel plan, we often use travel sites. However, there is a problem that it is difficult to decide a travel destination because the amount of information including users’ reviews is too large. Also, usually, travel information is separately registered for each destination (e.g. sightseeing place), which is difficult to use for those who have not yet decided the destination they want to go to. Therefore, the authors set a research goal to make it possible to choose a travel destination without having to browse a lot of travel information when making a travel plan, and developed a web service for recommending travel plans, called Tabi-gator (Travel navigator in English). Tabi-gator automatically creates several questions to diagnose user preferences with machine-learning technology, and then recommends a travel plan that is suitable for the user’s preference.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Survey on Travel in Japan - 70% worry about planning-fatigue (2018). https://www.tabikobo.com/company/news/press/2018/06/180605. (in Japanese)
Ahn, S., Kang, J., Park, S.: What makes the difference between popular games and unpopular games? ICIC Express Lett. 11(12), 1729–1737 (2017)
Kurihara, K., Shoji, Y., Fujita, S., Durst, J.: Target-Topic Aware Doc2Vec for Short Sentence Retrieval from User Generated Content (2019). http://shoji-lab.jp/research_paper/iiWAS2019_shoji_TTA-D2V.pdf
Erkan G., Radev, D.R.: LexRank - Graph-based Lexical Centrality as Salience in Text Summarization (2004). http://www.cs.cmu.edu/afs/cs/project/jair/pub/volume22/erkan04a-html/erkan04a.html
Kudo, T. FMeCab - Yet Another Part-of-Speech and Morphological Analyzer (2019).https://taku910.github.io/mecab/
mecab-ipadic-NEologd: Neologism dictionary for MeCab (2019). https://github.com/neologd/mecab-ipadic-NEologd/blob/master/README.ja.md
Lau, J.H. and Baldwin, T.: An Empirical Evaluation of Doc2Vec with Practical Insights into Document Embedding Generation (2016). https://arxiv.org/abs/1607.05368
models.doc2vec - Doc2vec paragraph embeddings (2019). https://radimrehurek.com/gensim /models/doc2vec.html
models.word2vec - Word2vec embeddings (2019). https://radimrehurek.com/gensim/models/word2vec.html
gensim, Free Python Library (2020). https://radimrehurek.com/gensim/
https://www.python.org/ (2019)
Acknowledgment
This work was supported by JSPS KAKENHI Number 16K00506.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ichimura, S. (2020). Travel Plan Recommendation Based on Review Analysis and Preference Diagnosis. In: Nolte, A., Alvarez, C., Hishiyama, R., Chounta, IA., Rodríguez-Triana, M., Inoue, T. (eds) Collaboration Technologies and Social Computing . CollabTech 2020. Lecture Notes in Computer Science(), vol 12324. Springer, Cham. https://doi.org/10.1007/978-3-030-58157-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-58157-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58156-5
Online ISBN: 978-3-030-58157-2
eBook Packages: Computer ScienceComputer Science (R0)