Morgan Harvey

Engaging and maintaining a sense of being informed: Understanding the tasks motivating twitter search

Micro‐blogging services such as Twitter represent constantly evolving, user‐generated sources of information. Previous studies show that users search such content regularly but are often dissatisfied with current search facilities. We argue that an enhanced understanding of the motivations for search would aid the design of improved search systems, better reflecting what people need. Building on previous research, we present qualitative analyses of two sources of data regarding how and why people search Twitter. The first, a diary study (p = 68), provides descriptions of Twitter information needs (n = 117) and important meta‐data from active study participants. The second data set was established by collecting first‐person descriptions of search behavior (n = 388) tweeted by twitter users themselves (p = 381) and complements the first data set by providing similar descriptions from a more plentiful source. The results of our analyses reveal numerous characteristics of Twitter search that differentiate it from more commonly studied search domains, such as web search. The findings also shed light on some of the difficulties users encounter. By highlighting examples that go beyond those previously published, this article adds to the understanding of how and why people search such content. Based on these new insights, we conclude with a discussion of possible design implications for search systems that index micro‐blogging content.

Bayesian latent variable models for collaborative item rating prediction

Collaborative filtering systems based on ratings make it easier for users to find content of interest on the Web and as such they constitute an area of much research. In this paper we first present a Bayesian latent variable model for rating prediction that models ratings over each users latent interests and also each items latent topics. We describe a Gibbs sampling procedure that can be used to estimate its parameters and show by experiment that it is competitive with the gradient descent SVD methods commonly used in state-of-the-art systems. We then proceed to make an important and novel extension to this model, enhancing it with user-dependent and item-dependant biases to significantly improve rating estimation. We show by experiment on a large set of real ratings data that these models are able to outperform 3 common baselines, including a very competitive and modern SVD-based model. Furthermore we illustrate other advantages of our approach beyond simply its ability to provide more accurate ratings and show that it is able to perform better on the common and important case where the user profile is short.

Understanding re-finding behavior in naturalistic email interaction logs

In this paper we present a longitudinal, naturalistic study of email behavior (n=47) and describe our efforts at isolating re-finding behavior in the logs through various qualitative and quantitative analyses. The presented work underlines the methodological challenges faced with this kind of research, but demonstrates that it is possible to isolate re-finding behavior from email interaction logs with reasonable accuracy. Using the approaches developed we uncover interesting aspects of email re-finding behavior that have so far been impossible to study, such as how various features of email-clients are used in re-finding and the difficulties people encounter when using these. We explain how our findings could influence the design of email-clients and outline our thoughts on how future, more in depth analyses, can build on the work presented here to achieve a fuller understanding of email behavior and the support that people need.

Towards query log based personalization using topic models

We investigate the utility of topic models for the task of personalizing search results based on information present in a large query log. We define generative models that take both the user and the clicked document into account when estimating the probability of query terms. These models can then be used to rank documents by their likelihood given a particular query and user pair.

Remembering through lifelogging: A survey of human memory augmentation

Human memory is unquestionably a vital cognitive ability but one that can often be unreliable. External memory aids such as diaries, photos, alarms and calendars are often employed to assist in remembering important events in our past and future. The recent trend for lifelogging, continuously documenting ones life through wearable sensors and cameras, presents a clear opportunity to augment human memory beyond simple reminders and actually improve its capacity to remember. This article surveys work from the fields of computer science and psychology to understand the potential for such augmentation, the technologies necessary for realising this opportunity and to investigate what the possible benefits and ethical pitfalls of using such technology might be.

Tripartite hidden topic models for personalised tag suggestion

Social tagging systems provide methods for users to categorise resources using their own choice of keywords (or “tags”) without being bound to a restrictive set of predefined terms. Such systems typically provide simple tag recommendations to increase the number of tags assigned to resources. In this paper we extend the latent Dirichlet allocation topic model to include user data and use the estimated probability distributions in order to provide personalised tag suggestions to users. We describe the resulting tripartite topic model in detail and show how it can be utilised to make personalised tag suggestions. Then, using data from a large-scale, real life tagging system, test our system against several baseline methods. Our experiments show a statistically significant increase in performance of our model over all key metrics, indicating that the model could be successfully used to provide further social tagging tools such as resource suggestion and collaborative filtering.

You Are What You Eat: Learning User Tastes for Rating Prediction

Poor nutrition is one of the major causes of ill-health and death in the western world and is caused by a variety of factors including lack of nutritional understanding and preponderance towards eating convenience foods. We wish to build systems which can recommend nutritious meal plans to users, however a crucial pre-requisite is to be able to recommend recipes that people will like. In this work we investigate key factors contributing to how recipes are rated by analysing the results of a longitudinal study (n=124) in order to understand how best to approach the recommendation problem. We identify a number of important contextual factors which can influence the choice of rating. Based on this analysis, we construct several recipe recommendation models that are able to leverage understanding of users likes and dislikes in terms of ingredients and combinations of ingredients and in terms of nutritional content. Via experiment over our dataset we are able to show that these models can significantly outperform a number of competitive baselines.

Towards Automatic Meal Plan Recommendations for Balanced Nutrition

Food recommenders have been touted as a useful tool to help people achieve a healthy diet. Here we incorporate nutrition into the recommender problem by examining the feasibility of algorithmically creating daily meal plans for a sample of user profiles (n=100), combined with a diverse set of food preference data (n=64) collected in a natural setting. Our analyses demonstrate it is possible to recommend plans for a large percentage of users which meet the guidelines set out by international health agencies

Learning by Example: Training Users with High-quality Query Suggestions

The queries submitted by users to search engines often poorly describe their information needs and represent a potential bottleneck in the system. In this paper we investigate to what extent it is possible to aid users in learning how to formulate better queries by providing examples of high-quality queries interactively during a number of search sessions. By means of several controlled user studies we collect quantitative and qualitative evidence that shows: (1) study participants are able to identify and abstract qualities of queries that make them highly effective, (2) after seeing high-quality example queries participants are able to themselves create queries that are highly effective, and, (3) those queries look similar to expert queries as defined in the literature. We conclude by discussing what the findings mean in the context of the design of interactive search systems.

Exploring query patterns in email search

Despite Email being the most popular communication medium currently in use and that people have been shown to regularly re-use messages, very little is known about how people actually search within email clients. In this paper we present a detailed analysis of email search behaviour obtained from a study of 47 users. We uncover a number of behavioral patterns that contrast with those previously observed in web search. From our findings, we describe ways in which email search could be improved and conclude with a short discussion of possible future work.