Men's experiences of receiving objective feedback on physical activity and other indicators of health risk, within the context of a gender-sensitised weight loss intervention

Receiving personalised feedback on body mass index and other health risk indicators may prompt behaviour change. Few studies have investigated men’s reactions to receiving objective feedback on such measures and detailed information on physical activity and sedentary time. The aim of my research was to understand the meanings different forms of objective feedback have for overweight/obese men, and to explore whether these varied between groups. Participants took part in Football Fans in Training, a gender-sensitised, weight loss programme delivered via Scottish Professional Football Clubs. Semi-structured interviews were conducted with 28 men, purposively sampled from four clubs to investigate the experiences of men who achieved and did not achieve their 5% weight loss target. Data were analysed using the principles of thematic analysis and interpreted through Self-Determination Theory and sociological understandings of masculinity. Several factors were vital in supporting a ‘motivational climate’ in which men could feel ‘at ease’ and adopt self-regulation strategies: the ‘place’ was described as motivating, whereas the ‘people’ (other men ‘like them’; fieldwork staff; community coaches) provided supportive and facilitative roles. Men who achieved greater weight loss were more likely to describe being motivated as a consequence of receiving information on their objective health risk indicators. They continued using self-monitoring technologies after the programme as it was enjoyable; or they had redefined themselves by integrating new-found activities into their lives and no longer relied on external technologies/feedback. They were more likely to see post-programme feedback as confirmation of success, so long as they could fully interpret the information. Men who did not achieve their 5% weight loss reported no longer being motivated to continue their activity levels or self-monitor them with a pedometer. Social support within the programme appeared more important. These men were also less positive about objective post-programme feedback which confirmed their lack of success and had less utility as a motivational tool. Providing different forms of objective feedback to men within an environment that has intrinsic value (e.g. football club setting) and congruent with common cultural constructions of masculinity, appears more conducive to health behaviour change.

The role of context in image annotation and recommendation

With the rise of smart phones, lifelogging devices (e.g. Google Glass) and popularity of image sharing websites (e.g. Flickr), users are capturing and sharing every aspect of their life online producing a wealth of visual content. Of these uploaded images, the majority are poorly annotated or exist in complete semantic isolation making the process of building retrieval systems difficult as one must firstly understand the meaning of an image in order to retrieve it. To alleviate this problem, many image sharing websites offer manual annotation tools which allow the user to “tag” their photos, however, these techniques are laborious and as a result have been poorly adopted; Sigurbjörnsson and van Zwol (2008) showed that 64% of images uploaded to Flickr are annotated with < 4 tags. Due to this, an entire body of research has focused on the automatic annotation of images (Hanbury, 2008; Smeulders et al., 2000; Zhang et al., 2012a) where one attempts to bridge the semantic gap between an image’s appearance and meaning e.g. the objects present. Despite two decades of research the semantic gap still largely exists and as a result automatic annotation models often offer unsatisfactory performance for industrial implementation. Further, these techniques can only annotate what they see, thus ignoring the “bigger picture” surrounding an image (e.g. its location, the event, the people present etc). Much work has therefore focused on building photo tag recommendation (PTR) methods which aid the user in the annotation process by suggesting tags related to those already present. These works have mainly focused on computing relationships between tags based on historical images e.g. that NY and timessquare co-exist in many images and are therefore highly correlated. However, tags are inherently noisy, sparse and ill-defined often resulting in poor PTR accuracy e.g. does NY refer to New York or New Year? This thesis proposes the exploitation of an image’s context which, unlike textual evidences, is always present, in order to alleviate this ambiguity in the tag recommendation process. Specifically we exploit the “what, who, where, when and how” of the image capture process in order to complement textual evidences in various photo tag recommendation and retrieval scenarios. In part II, we combine text, content-based (e.g. # of faces present) and contextual (e.g. day-of-the-week taken) signals for tag recommendation purposes, achieving up to a 75% improvement to precision@5 in comparison to a text-only TF-IDF baseline. We then consider external knowledge sources (i.e. Wikipedia & Twitter) as an alternative to (slower moving) Flickr in order to build recommendation models on, showing that similar accuracy could be achieved on these faster moving, yet entirely textual, datasets. In part II, we also highlight the merits of diversifying tag recommendation lists before discussing at length various problems with existing automatic image annotation and photo tag recommendation evaluation collections. In part III, we propose three new image retrieval scenarios, namely “visual event summarisation”, “image popularity prediction” and “lifelog summarisation”. In the first scenario, we attempt to produce a rank of relevant and diverse images for various news events by (i) removing irrelevant images such memes and visual duplicates (ii) before semantically clustering images based on the tweets in which they were originally posted. Using this approach, we were able to achieve over 50% precision for images in the top 5 ranks. In the second retrieval scenario, we show that by combining contextual and content-based features from images, we are able to predict if it will become “popular” (or not) with 74% accuracy, using an SVM classifier. Finally, in chapter 9 we employ blur detection and perceptual-hash clustering in order to remove noisy images from lifelogs, before combining visual and geo-temporal signals in order to capture a user’s “key moments” within their day. We believe that the results of this thesis show an important step towards building effective image retrieval models when there lacks sufficient textual content (i.e. a cold start).