Research Output
1 - 10 of 53
Publication
A multi-criteria evaluation of a user generated content based recommender system
2011-10-23, Garcia Esparza, Sandra, O'Mahony, Michael P., Smyth, Barry
The Social Web provides new and exciting sources of information that may be used by recommender systems as a complementary source of recommendation knowledge. For example, User-Generated Content, such as reviews, tags, comments, tweets etc. can provide a useful source of item information and user preference data, if a clear signal can be extracted from the inevitable noise that exists within these sources. In previous work we explored this idea, mining term-based recommendation knowledge from user reviews, to develop a recommender that compares favourably to conventional collaborative-filtering style techniques across a range of product types. However, this previous work focused solely on recommendation accuracy and it is now well accepted in the literature that accuracy alone tells just part of the recommendation story. For example, for many, the promise of recommender systems lies in their ability to surprise with novel recommendations for less popular items that users might otherwise miss. This makes for a riskier recommendation prospect, of course, but it could greatly enhance the practical value of recommender systems to end-users. In this paper we analyse our User-Generated Content (UGC) approach to recommendation using metrics such as novelty, diversity, and coverage and demonstrate superior performance, when compared to conventional user-based and item- based collaborative filtering techniques, while highlighting a number of interesting performance trade-offs.
Publication
Unsupervised Retrieval of Attack Profiles in Collaborative Recommender Systems
2008-04, Bryan, Kenneth, O'Mahony, Michael P., Cunningham, Pádraig
Trust, reputation and recommendation are key components of successful ecommerce systems. However, ecommerce systems are also vulnerable in this respect because there are opportunities for sellers to gain advantage through manipulation of reputation and recommendation. One such vulnerability is the use of fraudulent user profiles to boost (or damage) the ratings of items in an online recommender system. In this paper we cast this problem as a problem of detecting anomalous structure in network analysis and propose a novel mechanism for detecting this anomalous structure. We present an evaluation that shows that this approach is effective at uncovering the types of recommender systems attack described in the literature.
Publication
Combining similarity and sentiment in opinion mining for product recommendation
2016-04, Dong, Ruihai, O'Mahony, Michael P., Schaal, Markus, McCarthy, Kevin, Smyth, Barry
In the world of recommender systems, so-called content-based methods are an important approach that rely on the availability of detailed product or item descriptions to drive the recommendation process. For example, recommendations can be generated for a target user by selecting unseen products that are similar to the products that the target user has liked or purchased in the past. To do this, content-based methods must be able to compute the similarity between pairs of products (unseen products and liked products, for example) and typically this is achieved by comparing product features or other descriptive elements. The approach works well when product descriptions are readily available and when they are detailed enough to afford an effective similarity comparison. But this is not always the case. Detailed product descriptions may not be available since they can be expensive to create and maintain. In this article we consider another source of product descriptions in the form of the user-generated reviews that frequently accompany products on the web. We ask whether it is possible to mine these reviews, unstructured and noisy as they are, to produce useful product descriptions that can be used in a recommendation system. In particular we describe a novel approach to product recommendation that harnesses not only the features that can be mined from user-generated reviews but also the expressions of sentiment that are associated with these features. We present a recommendation ranking strategy that combines similarity and sentiment to suggest products that are similar but superior to a query product according to the opinion of reviewers, and we demonstrate the practical benefits of this approach across a variety of Amazon product domains.
Publication
From Opinions to Recommendations
2018-05-03, O'Mahony, Michael P., Smyth, Barry
Traditionally, recommender systems have relied on user preference data (such as ratings) and product descriptions (such as meta-data) as primary sources of recommendation knowledge. More recently, new sources of recommendation knowledge in the form of social media information and other kinds of user-generated content have emerged as viable alternatives. For example, services such as Twitter, Facebook, Amazon and TripAdvisor provide a rich source of user opinions, positive and negative, about a multitude of products and services. They have the potential to provide recommender systems with access to the fine-grained opinions of real users based on real experiences. This chapter will explore how product opinions can be mined from such sources and can be used as the basis for recommendation tasks. We will draw on a number of concrete case-studies to provide different examples of how opinions can be extracted and used in practice.
Publication
Towards tagging and categorization for micro-blogs
2010-08-30, Garcia Esparza, Sandra, O'Mahony, Michael P., Smyth, Barry
Abstract. Micro-blogging services are becoming very popular among users who want to share local or global news, their knowledge or their opinions on the real-time web. Lately, users are also using these services to search for information, and some services include tag or category information
to better facilitate search. However, these tags are typically free-form in nature with users permitted to adopt their own conventions without restriction, which can make the set of tags noisy and sparse. A
solution to this problem is to recommend tags (or categories) to users. Our work represents an initial study in the recommendation of categories for short-form messages in order to provide for better search and message filtering. In particular, we describe how such real-time web data can be used as a source of indexing and retrieval information for category recommendation. An evaluation performed on two different micro-blogging datasets indicates that promising performance is achieved by our approach.
Publication
Using readability tests to predict helpful product reviews
2010-04-28, O'Mahony, Michael P., Smyth, Barry
User-generated content provides online consumers with a wealth of information. Given the ever-increasing quantity of available content and the lack of quality control applied to this content, there is a clear need to enhance the user experience when it comes to effectively leveraging this vast information source. In this paper, we address these issues in the context of user-generated product reviews. We expand
on recent work to consider the performance of structural and readability feature sets on the classification of helpful product reviews. Our findings, based on a large-scale evaluation of TripAdvisor and Amazon reviews, indicate that structural and readability features are useful predictors for Amazon product reviews but less so for TripAdvisor hotel reviews.
Publication
Mining the Real-Time Web: A Novel Approach to Product Recommendation
2012-05, Garcia Esparza, Sandra, O'Mahony, Michael P., Smyth, Barry
Real-time web (RTW) services such as Twitter allow users to express their opinions and interests, often expressed in the form of short text messages providing abbreviated and highly personalized commentary in real-time. Although this RTW data is far from the structured data (movie ratings, product features, etc.) that is familiar to recommender systems research, it can contain useful consumer reviews on products, services and brands. This paper describes how Twitter-like short-form messages can be leveraged as a source of indexing and retrieval information for product recommendation. In particular, we describe how users and products can be represented from the terms used in their associated reviews. An evaluation performed on four different product datasets from the Blippr service shows the potential of this type of recommendation knowledge, and the experiments show that our proposed approach outperforms a more traditional collaborative-filtering based approach.
Publication
The readability of helpful product reviews
2010-05-19, O'Mahony, Michael P., Smyth, Barry
Consumers frequently rely on user-generated product reviews to guide purchasing decisions. Given the ever increasing volume of such reviews and variations in review
quality, consumers require assistance to effectively leverage this vast information source. In this paper, we examine to what extent the readability of reviews is a predictor of review helpfulness. Using a supervised classification approach, our findings indicate that readability is a useful predictor for Amazon product reviews
but less so for TripAdvisor hotel reviews.
Publication
Evaluating the Relative Performance of Neighbourhood-Based Recommender Systems
2014-06-20, Corona, Humberto, Jerbi, Houssem, O'Mahony, Michael P.
Neighbourhood-based recommender systems are a class of collaborative filtering algorithms, which rely on finding like-minded users to generate recommendations, automating what is usually known as word-of-mouth. These systems attempt to solve the information overload problem by presenting the user with relevant items. However, there is evidence showing that these algorithms may contribute to the filter bubble problem, making it harder for the user to find interesting items which are non-popular. In this paper we propose a novel evaluation of the performance and biases of the two most common neighbourhood-based approaches: user k-nearest neighbour collaborative filtering (UKNN ), and item k-nearest neighbour collaborative filtering (IKNN). We propose an evaluation which considers the size of the neighbourhood, finding that optimising for accuracy in UKNN algorithms leads to a poor performance in terms of diversity, a higher bias towards popularity, and less unique recommendations, when compared to the IKNN approach.
Publication
Learning to recommend helpful hotel reviews
2009-10, O'Mahony, Michael P., Smyth, Barry
User-generated reviews are a common and valuable source of product information, yet little attention has been paid as to how best to present them to end-users. In this paper, we describe a classification-based recommender system that is designed to recommend the most helpful reviews for a given product. We present a large-scale evaluation of our approach using TripAdvisor hotel reviews, and we show that our approach
is capable of suggesting superior reviews compared to a number of alternative recommendation benchmarks.