Finding a Needle in a Haystack of Reviews: Cold Start Context-Based Hotel Recommender System Demo

Asher Levi; Osnat Mokryn; Christophe Diot; Nina Taft

doi:https://doi.org/10.1145/2365952.2366025

Abstract

Online hotel searching is a daunting task due to the wealth of online information. Reviews written by other travelers replace the word-of-mouth, yet turn the search into a time consuming task. Users do not rate enough hotels to enable a collaborative filtering based recommendation. Thus, a cold start recommender system is needed. This demo describes briefly our cold start hotel recommender system, which uses the text of the reviews as its main data. We define context groups based on reviews extracted from TripAdvisor.com and Venere.com. We introduce a novel weighted algorithm for text mining.We implemented our system which was used by the public to conduct 150 trip planning experiments. We compare our solution to the top suggestions of the mentioned web services and show that users were, on average, 20% more satisfied with our hotel recommendations. We outperform these web services even more in cities where hotel prices are high.

Original language	English
Pages	305–306
DOIs	https://doi.org/10.1145/2365952.2366025
State	Published - 2012
Externally published	Yes
Event	6th ACM conference on Recommender Systems (RecSys’12) - Duration: 9 Sep 2012 → …

Conference

Conference	6th ACM conference on Recommender Systems (RecSys’12)
Period	9/09/12 → …

Keywords

common traits
sentiment analysis
opinion/text mining
recommender systems
context-aware recommender systems

Access to Document

https://doi.org/10.1145/2365952.2366025

https://doi.org/10.1145/2365952.2366025

Cite this

@conference{80c2e90564954472a72d7779adf1c76d,

title = "Finding a Needle in a Haystack of Reviews: Cold Start Context-Based Hotel Recommender System Demo",

abstract = "Online hotel searching is a daunting task due to the wealth of online information. Reviews written by other travelers replace the word-of-mouth, yet turn the search into a time consuming task. Users do not rate enough hotels to enable a collaborative filtering based recommendation. Thus, a cold start recommender system is needed. This demo describes briefly our cold start hotel recommender system, which uses the text of the reviews as its main data. We define context groups based on reviews extracted from TripAdvisor.com and Venere.com. We introduce a novel weighted algorithm for text mining.We implemented our system which was used by the public to conduct 150 trip planning experiments. We compare our solution to the top suggestions of the mentioned web services and show that users were, on average, 20% more satisfied with our hotel recommendations. We outperform these web services even more in cities where hotel prices are high.",

keywords = "common traits, sentiment analysis, opinion/text mining, recommender systems, context-aware recommender systems",

author = "Asher Levi and Osnat Mokryn and Christophe Diot and Nina Taft",

year = "2012",

doi = "https://doi.org/10.1145/2365952.2366025",

language = "الإنجليزيّة",

pages = "305–306",

note = "6th ACM conference on Recommender Systems (RecSys{\textquoteright}12) ; Conference date: 09-09-2012",

}

TY - CONF

T1 - Finding a Needle in a Haystack of Reviews

T2 - 6th ACM conference on Recommender Systems (RecSys’12)

AU - Levi, Asher

AU - Mokryn, Osnat

AU - Diot, Christophe

AU - Taft, Nina

PY - 2012

Y1 - 2012

N2 - Online hotel searching is a daunting task due to the wealth of online information. Reviews written by other travelers replace the word-of-mouth, yet turn the search into a time consuming task. Users do not rate enough hotels to enable a collaborative filtering based recommendation. Thus, a cold start recommender system is needed. This demo describes briefly our cold start hotel recommender system, which uses the text of the reviews as its main data. We define context groups based on reviews extracted from TripAdvisor.com and Venere.com. We introduce a novel weighted algorithm for text mining.We implemented our system which was used by the public to conduct 150 trip planning experiments. We compare our solution to the top suggestions of the mentioned web services and show that users were, on average, 20% more satisfied with our hotel recommendations. We outperform these web services even more in cities where hotel prices are high.

AB - Online hotel searching is a daunting task due to the wealth of online information. Reviews written by other travelers replace the word-of-mouth, yet turn the search into a time consuming task. Users do not rate enough hotels to enable a collaborative filtering based recommendation. Thus, a cold start recommender system is needed. This demo describes briefly our cold start hotel recommender system, which uses the text of the reviews as its main data. We define context groups based on reviews extracted from TripAdvisor.com and Venere.com. We introduce a novel weighted algorithm for text mining.We implemented our system which was used by the public to conduct 150 trip planning experiments. We compare our solution to the top suggestions of the mentioned web services and show that users were, on average, 20% more satisfied with our hotel recommendations. We outperform these web services even more in cities where hotel prices are high.

KW - common traits

KW - sentiment analysis

KW - opinion/text mining

KW - recommender systems

KW - context-aware recommender systems

U2 - https://doi.org/10.1145/2365952.2366025

DO - https://doi.org/10.1145/2365952.2366025

M3 - مختصر

SP - 305

EP - 306

Y2 - 9 September 2012

ER -