Michael P. O’Mahony

Robust Collaborative Recommendation

Collaborative recommender systems are vulnerable to malicious users who seek to bias their output, causing them to recommend (or not recommend) particular items. This problem has been an active research topic since 2002. Researchers have found that the most widely-studied memory-based algorithms have significant vulnerabilities to attacks that can be fairly easily mounted. This chapter discusses these findings and the responses that have been investigated, especially detection of attack profiles and the implementation of robust recommendation algorithms.

Opinionated Product Recommendation

In this paper we describe a novel approach to case-based product recommendation. It is novel because it does not leverage the usual static, feature-based, purely similarity-driven approaches of traditional case-based recommenders. Instead we harness experiential cases, which are automatically mined from user generated reviews, and we use these as the basis for a form of recommendation that emphasises similarity and sentiment. We test our approach in a realistic product recommendation setting by using live-product data and user reviews.

A Case Study of Collaboration and Reputation in Social Web Search

Although collaborative searching is not supported by mainstream search engines, recent research has highlighted the inherently collaborative nature of many Web search tasks. In this article, we describe HeyStaks, a collaborative Web search framework that is designed to complement mainstream search engines. At search time, HeyStaks learns from the search activities of other users and leverages this information to generate recommendations based on results that others have found relevant for similar searches. The key contribution of this article is to extend the HeyStaks social search model by considering the search expertise, or reputation, of HeyStaks users and using this information to enhance the result recommendation process. In particular, we propose a reputation model for HeyStaks users that utilise the implicit collaboration events that take place between users as recommendations are made and selected. We describe a live-user trial of HeyStaks that demonstrates the relevance of its core recommendations and the ability of the reputation model to further improve recommendation quality. Our findings indicate that incorporating reputation into the recommendation process further improves the relevance of HeyStaks recommendations by up to 40%.

Further Experiments in Opinionated Product Recommendation

In this paper we build on recent work on case-based product recommendation focused on generating rich product descriptions for use in a recommendation context by mining user-generated reviews. This is in contrast to conventional case-based approaches which tend to rely on case descriptions that are based on available meta-data or catalog descriptions. By mining user-generated reviews we can produce product descriptions that reflect the opinions of real users and combine notions of similarity and opinion polarity (sentiment) during the recommendation process. In this paper we compare different variations on our review-mining approach, one based purely on features found in reviews, one seeded by features that are available from meta-data, and one hybrid approach that combines both approaches. We evaluate these approaches across a variety of datasets form the travel domain.

From Opinions to Recommendations

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.

Mining Features and Sentiment from Review Experiences

Supplementing product information with user-generated content such as ratings and reviews can help to convert browsers into buyers. As a result this type of content is now front and centre for many major e-commerce sites such as Amazon. We believe that this type of content can provide a rich source of valuable information that is useful for a variety of purposes. In this work we are interested in harnessing past reviews to support the writing of new useful reviews, especially for novice contributors. We describe how automatic topic extraction and sentiment analysis can be used to mine valuable information from user-generated reviews, to make useful suggestions to users at review writing time about features that they may wish to cover in their own reviews. We describe the results of a live-user trial to show how the resulting system is capable of delivering high quality reviews that are comparable to the best that sites like Amazon have to offer in terms of information content and helpfulness.

Towards the Profiling of Twitter Users for Topic-Based Filtering

There is no doubting the incredible impact of Twitter on how we communicate, access and share information online. Currently users can follow other users or hashtags in order to benefit from a stream of data from people they trust or on topics that matter to them. However at the moment the following granularity of Twitter means that users cannot limit their information streams to a set of topics by a given user. Thus, even the most carefully curated information streams can quickly become polluted with extraneous content. In this paper we describe our initial steps to improve this situation by proposing a profiling approach that can be used for information filtering purposes as well as recommendation purposes. First, we demonstrate that it is feasible to automatically profile the interests of users by using machine learning techniques to classify the pages that they share via their tweets. We then go on to describe how this profiling mechanism can be used to organise and filter Twitter information streams. In particular we present a system that provides for a more fine-grained way to follow users on specific topics and thereby refine the standard Twitter timeline based on a user’s core topical interests.

Module Advisor: Guiding Students with Recommendations

Personalised recommendations feature prominently in many aspects of our lives, from the movies we watch, to the news we read, and even the people we date. However, one area that is still relatively underdeveloped is the educational sector where recommender systems have the potential to help students to make informed choices about their learning pathways. We aim to improve the way students discover elective modules by using a hybrid recommender system that is specifically designed to help students to better explore available options. By combining notions of content-based similarity and diversity, based on structural information about the space of modules, we can improve the discoverability of long-tail options that may uniquely suit students’ preferences and aspirations.

Collaboration, Reputation and Recommender Systems in Social Web Search

Modern web search engines have come to dominate how millions of people find the information that they are looking for online. While the sheer scale and success of the leading search engines is a testimony to the scientific and engineering progress that has been made over the last two decades, mainstream search is not without its challenges. Mainstream search engines continue to provide a largely one-size-fits-all service to their user-base, ultimately limiting the relevance of their result-lists. And they have only very recently begun to consider how the rise of the social web may support novel approaches to search and discovery, or how such signals can be used to inform relevance. In this chapter we will explore recent research which aims to do just that: to make web search a more personal and collaborative experience and to leverage important information such as the reputation of searchers during result-ranking. In short we look towards a more social future for mainstream search.

Unsupervised Topic Extraction for the Reviewer's Assistant

User generated reviews are now a familiar and valuable part of most ecommerce sites since high quality reviews are known to influence purchasing decisions. In this paper we describe work on the Reviewer’s Assistant (RA), which is a recommendation system that is designed to help users to write better reviews. It does this by suggesting relevant topics that they may wish to discuss based on the product they are reviewing and the content of their review so far. We build on prior work and describe an unsupervised topic extraction module for the RA system that enhances the system’s ability to automatically adapt to new content categories and application domains. Our main contribution includes the results of a controlled, live-user study to show that the RA system is capable of supporting users to create reviews that enjoy higher quality ratings than Amazon’s own high quality reviews, even without using manually created topic models.