By incorporating healthiness into the food recommendation / ranking process we have the potential to improve the eating habits of a growing number of people who use the Internet as a source of food inspiration. In this paper, using insights gained from various data sources, we explore the feasibility of substituting meals that would typically be recommended to users with similar, healthier dishes. First, by analysing a recipe collection sourced from Allrecipes.com, we quantify the potential for nding replacement recipes, which are comparable but have di erent nutritional characteristics and are nevertheless highly rated by users. Building on this, we present two controlled user studies (n=107, n=111) investigating how people perceive and select recipes. We show participants are unable to reliably identify which recipe contains most fat due to their answers being biased by lack of information, misleading cues and limited nutritional knowledge on their part. By applying machine learning techniques to predict the preferred recipes, good performance can be achieved using low-level image features and recipe meta-data as predictors. Despite not being able to consciously determine which of two recipes contains most fat, on average, participants select the recipe with the most fat as their preference. The importance of image features reveals that recipe choices are often visually driven. A nal user study (n=138) investigates to what extent the predictive models can be used to select recipe replacements such that users can be "nudged" towards choosing healthier recipes. Our ndings have important implications for online food systems. KEYWORDSFood RecSys; human decision making; behavioural change; information behaviour ACM Reference format:

In an attempt to market their services and connect with potential users, and particularly young people, many libraries are opening accounts on social media platforms. Research suggests a contradiction between the advice relating to marketing and that regarding the use of social media in libraries, with the former emphasising the importance of the user at the centre of all considerations and the latter placing library staff as central to decisions. In this work we attempt to re-address this imbalance by surveying the current state of library activity on Twitter and, by means of questionnaires, investigate the experiences and motivations of librarians (n=58) in using social media and whether students (n=498) are willing to engage with the library in this manner and why. Our findings confirm that libraries in the sector are indeed struggling to foster interest in their social media activities and go some way to understanding why this is so, leading to a number of conclusions and recommendations for practitioners. KeywordsLibrary 2.0, social media, marketing IntroductionAfter only a decade in existence, social media (henceforth 'SM)' has become a significant presence in our lives, not just personally but also professionally (Brenner and Smith, 2012;Bradley, 2015). Millennials employ SM tools as their primary communicative channels (Read et al. 2012) and make little distinction between their online and offline social interactions (Brook 2012). As a direct result of this, in the library and information profession there has been increasing uptake of these tools with over 70% of libraries worldwide now using SM tools and 60% having had their accounts for 3 years or more and 30% of librarians posting daily (McCallum 2015). Research suggests that conversations about libraries and their resources take place on Twitter and Facebook, regardless of whether the library has a presence on them or not (Bradley 2015).SM affords the library the opportunity to get out from behind the desk and go to where the conversations are, thus becoming part of this discourse (Bradley 2015). However, the ease of transition to using these new tools has led to overconfidence in what they can achieve. Studies indicate that, although the utilisation of such applications in libraries has been a fairly positive change (Anttiroiko and Savolainen 2011), this brings with it the need to develop new skills and competencies. This is something which many find intimidating and is not representative of the kinds of skills the majority of librarians already possess (Vanwynsberghe et al. 2015;Huvila et al. 2013). Even if libraries do begin to actively use such services and train their staff appropriately, it is not clear that users will necessarily respond with any real enthusiasm (Swanson 2012). It is not enough to understand how to use such tools; to use them effectively libraries need to examine and understand the behaviour, culture and etiquette of the user community (Luo et al. 2013).Existing research is somewhat sparse and mostly contradictory, wi...

Personalisation is an important area in the field of IR that attempts to adapt ranking algorithms so that the results returned are tuned towards the searcher's interests. In this work we use query logs to build personalised ranking models in which user profiles are constructed based on the representation of clicked documents over a topic space. Instead of employing a human-generated ontology, we use novel latent topic models to determine these topics. Our experiments show that by subtly introducing user profiles as part of the ranking algorithm, rather than by re-ranking an existing list, we can provide personalised ranked lists of documents which improve significantly over a non-personalised baseline. Further examination shows that the performance of the personalised system is particularly good in cases where prior knowledge of the search query is limited.

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.

No abstract