Category: Social Data

Optimizing Travel Destinations Based on User Preferences

by Julia Kiseleva (TU Eindhoven), Melanie Müller (Booking.com), Lucas Bernardi (Booking.com), Chad Davis (Booking.com), Ivan Kovacek (Booking.com), Mats Stafseng Einarsen (Booking.com), Jaap Kamps (University of Amsterdam), Alexander Tuzhilin (New York University), Djoerd Hiemstra

Recommendation based on user preferences is a common task for e-commerce websites. New recommendation algorithms are often evaluated by offline comparison to baseline algorithms such as recommending random or the most popular items. Here, we investigate how these algorithms themselves perform and compare to the operational production system in large scale online experiments in a real-world application. Specifically, we focus on recommending travel destinations at Booking.com, a major online travel site, to users searching for their preferred vacation activities. To build ranking models we use multi-criteria rating data provided by previous users after their stay at a destination. We implement three methods and compare them to the current baseline in Booking.com: random, most popular, and Naive Bayes. Our general conclusion is that, in an online A/B test with live users, our Naive-Bayes based ranker increased user engagement significantly over the current online system.

To be presented at SIGIR 2015, the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, on 12 August in Santiago de Chile.

[download preprint]

UT-DB: An Experimental Study on Sentiment Analysis in Twitter

Zhemin Zhu, Djoerd Hiemstra, Peter Apers, and Andreas Wombacher

This paper describes our system for participating SemEval 2013 Task 2-B: Sentiment Analysis in Twitter. Given a message, our system classifies whether the message is positive, negative or neutral sentiment. It uses a co-occurrence rate model. The training data are constrained to the data provided by the task organizers (No other tweet data are used). We consider 9 types of features and use a subset of them in our submitted system. To see the contribution of each type of features, we do experimental study on features by leaving one type of features out each time. Results suggest that unigrams are the most important features, bigrams and POS tags seem not helpful, and stopwords should be retained to achieve the best results. The overall results of our system are promising regarding the constrained features and data we use.

[download pdf]