Discovery of latent subcommunities in a blog's readership

The blogosphere has grown to be a mainstream forum of social interaction as well as a commercially attractive source of information and influence. Tools are needed to better understand how communities that adhere to individual blogs are constituted in order to facilitate new personal, socially-focused browsing paradigms, and understand how blog content is consumed, which is of interest to blog authors, big media, and search. We present a novel approach to blog subcommunity characterization by modeling individual blog readers using mixtures of an extension to the LDA family that jointly models phrases and time, Ngram Topic over Time (NTOT), and cluster with a number of similarity measures using Affinity Propagation. We experiment with two datasets: a small set of blogs whose authors provide feedback, and a set of popular, highly commented blogs, which provide indicators of algorithm scalability and interpretability without prior knowledge of a given blog. The results offer useful insight to the blog authors about their commenting community, and are observed to offer an integrated perspective on the topics of discussion and members engaged in those discussions for unfamiliar blogs. Our approach also holds promise as a component of solutions to related problems, such as online entity resolution and role discovery.

Supermarket Healthy Eating for Life (SHELf): protocol of a randomised controlled trial promoting healthy food and beverage consumption through price reduction and skill-building strategies

Background: In the context of rising food prices, there is a need for evidence on the most effective approaches for promoting healthy eating. Individually-targeted behavioural interventions for increasing food-related skills show promise, but are unlikely to be effective in the absence of structural supports. Fiscal policies have been advocated as a means of promoting healthy eating and reducing obesity and nutrition-related disease, but there is little empirical evidence of their effectiveness. This paper describes the Supermarket Healthy Eating for LiFe (SHELf) study, a randomised controlled trial to investigate effectiveness and cost-effectiveness of a tailored skill-building intervention and a price reduction intervention, separately and in combination, against a control condition for promoting purchase and consumption of healthy foods and beverages in women from high and low socioeconomic groups.
Methods/design: SHELf comprises a randomised controlled trial design, with participants randomised to receive either (1) a skill-building intervention; (2) price reductions on fruits, vegetables and low-joule soft drink beverages and water; (3) a combination of skill-building and price reductions; or (4) a control condition. Five hundred women from high and low socioeconomic areas will be recruited through a store loyalty card program and local media. Randomisation will occur on receipt of informed consent and baseline questionnaire. An economic evaluation from a societal perspective using a cost-consequences approach will compare the costs and outcomes between intervention and control groups.
Discussion: This study will build on a pivotal partnership with a major national supermarket chain and the Heart Foundation to investigate the effectiveness of intervention strategies aimed at increasing women’s purchasing and consumption of fruits and vegetables and decreased purchasing and consumption of sugar-sweetened beverages. It will be among the first internationally to examine the effects of two promising approaches - skill-building and price reductions - on diet amongst women.

Content structure discovery in educational videos using shared structures in the hierarchical hidden Markov models

In this paper, we present an application of the hierarchical HMM for structure discovery in educational videos. The HHMM has recently been extended to accommodate the concept of shared structure, ie: a state might multiply inherit from more than one parents. Utilising the expressiveness of this model, we concentrate on a specific class of video -educational videos - in which the hierarchy of semantic units is simpler and clearly defined in terms of topics and its subunits. We model the hierarchy of topical structures by an HHMM and demonstrate the usefulness of the model in detecting topic transitions.

Reliable aggregation on network traffic for web based knowledge discovery

The web is a rich resource for information discovery, as a result web mining is a hot topic. However, a reliable mining result depends on the reliability of the data set. For every single second, the web generate huge amount of data, such as web page requests, file transportation. The data reflect human behavior in the cyber space and therefore valuable for our analysis in various disciplines, e.g. social science, network security. How to deposit the data is a challenge. An usual strategy is to save the abstract of the data, such as using aggregation functions to preserve the features of the original data with much smaller space. A key problem, however is that such information can be distorted by the presence of illegitimate traffic, e.g. botnet recruitment scanning, DDoS attack traffic, etc. An important consideration in web related knowledge discovery then is the robustness of the aggregation method , which in turn may be affected by the reliability of network traffic data. In this chapter, we first present the methods of aggregation functions, and then we employe information distances to filter out anomaly data as a preparation for web data mining.

Towards discovery of influence and personality traits through social link prediction

Estimation of a person’s influence and personality traits from social media data has many applications. We use social linkage criteria, such as number of followers and friends, as proxies to form corpora, from popular blogging site Livejournal, for examining two two-class classification problems: influential vs. non-influential, and extraversion vs. introversion. Classification is performed using automatically-derived psycholinguistic and mood-based features of a user’s textual messages. We experiment with three sub-corpora of 10000 users each, and present the most effective predictors for each category. The best classification result, at 80%, is achieved using psycholinguistic features; e.g., influentials are found to use more complex language, than non-influentials, and use more leisure-related terms.

Discovery of activity structures using the hierarchical hidden Markov model

In building a surveillance system for monitoring people behaviours, it is important to understand the typical patterns of people's movement in the environment. This task is difficult when dealing with high-level behaviours. The flat model such as the hidden Markov model (HMM) is inefficient in differentiating between signatures of such behaviours. This paper examines structure learning for high-level behaviours using the hierarchical hidden Markov model (HHMM).We propose a two-phase learning algorithm in which the parameters of the behaviours at low levels are estimated first and then the structures and parameters of the behaviours at high levels are learned from multi-camera training data. Our algorithm is then evaluated using data from a real environment, demonstrating the robustness of the learned structure in recognising people's behaviour.

Associations between mothers’ perceptions of the cost of fruit and vegetables and children’s diets : Will children pay the price?

Background/Objectives:
Perceptions that fruit and vegetables are expensive are more common among the socio-economically disadvantaged groups and are linked to poor dietary outcomes. Such perceptions may be exacerbated in countries recently affected by natural disasters, where devastation of fruit and vegetable crops has resulted in increase in prices of fruit and vegetables. Examining the associations of perceptions of fruit and vegetable affordability and children's diets can offer insights into how the high prices of fruit and vegetables might have an impact on the diets of children.
Subjects/Methods:
We analysed the data from 546 socio-economically disadvantaged mother–child pairs to assess the relationship between maternal perceptions of fruit and vegetable affordability and the diets of their children.
Results:
Fruit consumption was lower among children whose mothers felt the cost of fruit was too high. Maternal perceptions of fruit and vegetable affordability were not associated with any other aspect of child's diet.
Conclusions:
Our results suggest a possible role for maternal perceptions of fruit affordability in children's diet, though further research is warranted.

Investment and oil price volatility

In this note, we consider the relationship between oil price volatility and firm returns for 560 firms listed on the New York Stock Exchange. Using daily time series data from 2000 to 2008, we find that oil price volatility increases firm returns for the majority of the firms in our sample.

On the welfare gains of price dispersion

Can price dispersion be associated with higher levels of welfare? To answer we compare two economies that differ only in the way prices are formed. In the first, sellers post a unique price–quantity pair, with no price dispersion. In the second, sellers post a quantity only and let prices be determined ex post by realized demand, resulting in price dispersion. We show that while agents trade lower quantities when prices are dispersed (an intensive margin effect), they also trade more often (an extensive margin effect). At low inflation, the extensive margin dominates making agents better off with price dispersion.

Transforming an academic library's spaces : an evaluation study of Deakin University Library at Burwood campus using TEALS discovery

Libraries worldwide are transforming their spaces to better align with the changing needs of their communities. The aim of this paper is to outline the process and outcome of an evaluation study of transformed academic library spaces at the Melbourne Burwood Campus using TEALS. In light of changing higher education practices and students learning preferences, Deakin University has been questioning the balance of informal learning spaces and more formal teaching and academic spaces across its campuses. Commissioned by Deakin University Library, TEALS (Tool for the Evaluation of Academic Library Spaces) was developed to evaluate academic library spaces. The Melbourne Burwood Campus library has undergone several phases of refurbishment to create a library environment that is centred around students’ needs and that supports their individual and group learning experiences. In addition, areas of the library yet to be improved will undergo a major redevelopment over the next year. Given this, carrying out an evaluation of the current spaces is timely to ensure that a better understanding of the impact of changes is achieved. The evaluation process involved: a review of architectural plans and space briefing documents; an observational study of spaces; focus groups with students and library staff; and an online survey of Students’ Library Experience. Use of the TEALS space evaluation tool along with an analysis of data collected during the evaluation process have provided significant insights into various dimensions of the quality of new library spaces. The areas of weakness and strength identified in the study will inform the next phase of Deakin University Library space redevelopment.

In support of hydrocarbon exploration and discovery using clouds

Seismic data gathered from the Hydrocarbon Exploration and Discovery Operation is essential to identify possible hydrocarbon existence in a geologically surveyed area. However, the discovery operation takes a long time to be completed and computational processing of the acquired data is often delayed. Hydrocarbon exploration may end up needlessly covering an area without any hydrocarbon traces due to lack of immediate feedback from geophysical experts. This feedback can only be given when the acquired seismic data is computationally processed, analysed and interpreted. In response, we propose a comprehensive model to facilitate Hydrocarbon Exploration and Discovery Operation using encryption, decryption, satellite transmission and clouds. The model details the logical design of Seismic Data Processing (SDP) that exploits clouds and the ability for geophysical experts to provide on-line decisions on how to progress the hydrocarbon exploration operation at a remote location. Initial feasibility assessment was carried out to support our model. The SDP, data encryption and encryption for the assessment were carried out on a private cloud. The assessment shows that the overall process of hydrocarbon exploration from data acquisition, satellite data transmission through to SDP could be executed in a short time and at low costs.