Event Based Multiple Tourism Themes’ Determination From Texts For Alternative Tourism Recommendations

Main Article Content

Nattapong Savavibool
Chaveevan Pechsiri


- This research aims to determine the multiple tourism themes based on attractiveness events expressed by the action verbs from the tourism web documents of the selected region. These several themes can be used for recommending tourists with alternative tourism theme choices. The problems of tourism themes’ acquisition from the web blog texts are to determine the touristic themes and to identify a touristic event base on a simple sentence or EDU Elementary Discourse Unit). This research proposes using the k-means clustering technique based on events expressed by verb phrases to determine the multiple tourism themes for a group of provinces within a region. Each cluster represents its own events while some of these events can be determined as the tourism themes by using verb-noun co-occurrences with the tourism event concepts. The result of the event-based tourism theme determination is evaluated by comparing to the answer set of the tourism highlight of each province provided by Tourism Authority of Thailand (http://thai.tourismthailand.org/), and our proposed methodology shows successfully results

Article Details

How to Cite
N. Savavibool and C. Pechsiri, “Event Based Multiple Tourism Themes’ Determination From Texts For Alternative Tourism Recommendations”, JIST, vol. 3, no. 1, pp. 1–7, Jun. 2012.
Research Article: Soft Computing (Detail in Scope of Journal)


1. U.H. Graneheim and B. Lundman, “Qualitative content analysis in nursing research: concepts, procedures and measures to achieve trustworthiness,” Nurse Education Today, vol. 24(2), pp. 105-112, 2004.

2. L. Carlson, D. Marcu, and M.E. Okurowski, “Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory,” In Current Directions in Discourse and Dialogue, pp. 85-112, 2003.

3. S. Loh, F. Lorenz, R. Saldana and D. Licthnow, “A tourism recommender system based on collaboration and text analysis,” Journal of Information Technology & Tourism, vol. 6, pp. 157–165, 2004.

4. Q. Mei, C. Zhai, “Discovering Evolutionary Theme Patterns from Text: an Exploration of Temporal Text Mining,” KDD '2005, 2005.

5. Q. Hao, R. Cai, C. Wang, R. Xiao, J. Yang, Y. Pang, and L. Zhang, “Equip Tourists with Knowledge Mined from Travelogues,” WWW '2010, 2010.

6. T. Kurashima, T. Tezuka. and Tanaka K, “Mining and Visualizing Local Experiences from Blog Entries,” DEXA’2006, 2006.

7. S. Sudprasert and A. Kawtrakul, “Thai Word Segmentation based on Global and Local Unsupervised Learning,” NCSEC’2003, 2003.

8. H. Chanlekha and A. Kawtrakul, “Thai Named Entity Extraction by incorporating Maximum Entropy Model with Simple Heuristic Information,” IJCNLP’2004, 2004.

9. J. Chareonsuk, T. Sukvakree and A. Kawtrakul, “Elementary Discourse unit Segmentation for Thai using Discourse Cue and Syntactic Information,” NCSEC’2005, 2005.

10. J. B. Macqueen, "Some Methods for classification and Analysis of Multivariate Observations," Proc. of 5th Berkeley Symposium on Mathematical Statistics and Probability, University of California Press, 1967.

11. K. V. Mardia, J. T. Kent and J. M. Bibby, Multivariate Analysis, Academic Press, 1979.