Robert Mcarthur's research while affiliated with Australian National University and other places

Publications (24)

Conference Paper
People's utterances are fundamentally different to other documents because they are more immediate and less thought through. While this makes them more natural - noisy and unstructured - it provides an unrivalled opportunity to see "inside" the author, to collect some context. The data requires analysis methods that have a relationship to human inf...
Conference Paper
Full-text available
Electronic discussion groups provide a convenient forum for individuals to share their experiences of chronic illness. The language use of individual participants, and the way their language shifts over time, may provide implicit indications of important shifts in sense-of-self. This paper relates experience with application of the hyperspace analo...
Article
A consequence of the explosion of information is diminishing awareness: disciplines are becoming increasingly specialized; individuals and groups are becoming ever more insular. This paper considers how awareness can be enhanced via text-based knowledge discovery. Knowledge representation is motivated from a socio-cognitive perspective. Concepts ar...
Conference Paper
We report on analysis of discussions in an online community of people with chronic illness using socio-cognitively motivated, automatically produced semantic spaces. The analysis aims to further the emerging theory of "transition" (how people can learn to incorporate the consequences of illness into their lives). An automatically derived representa...
Article
When a modern corporation empowers its staff to use blogs to communicate with colleagues, partners, suppliers and customers, the role of management in exercising oversight and guidance over the public speech of staff becomes dramatically challenged. This paper describes a computational solution to the interpretation of human-readable blog publishin...
Article
Diminishing awareness is a consequence of the information explosion: disciplines are becoming increasingly specialized; individuals are becoming ever more insular. This paper considers how awareness can be enhanced via abductive knowledge discovery the goal of which is to produce suggestions which can span disparate islands of knowledge. Knowledge...
Article
A consequence of the explosion of information is diminishing awareness: disciplines are becoming increasingly specialized; individuals and groups are becoming ever more insular. This paper considers how awareness can be enhanced via text-based knowledge discovery. Knowledge representation is motivated from a socio-cognitive perspective. Concepts ar...
Article
This paper is about finding explicit and implicit connections between people by mining semantic associations from their email communications. Following from a sociocognitive stance, we propose a model called HALe which automatically derives dimensional representations of words in a high dimensional context space from an email corpus. These dimensio...
Conference Paper
This paper is about finding explicit and implicit connections between people by mining semantic associations from their email communications. Following from a socio- cognitive stance, we propose a model called HALe which automatically derives dimensional representations of words in a high dimensional context space from an email corpus. These dimens...
Article
This chapter shows how to derive postsemantic context based on vector representations of words (described in Chap.8). The core problem is to discover relevant word associations in relation to seed words in the utterance. This may involve uncovering implicit associations or reweighting explicit associations more highly. The set of such associations...
Article
Introduction Chance discovery in online communities has many facets. It is the serendipitous meeting of two people with a background or interest in common (the interest being subsidiary to the community's raison d'tre). It is a solution to some problem that the community has, but that solution must come from without. In this chapter, we separate th...
Article
A number of conditions are necessary for the formation of `glue' to keep an online community together. One condition of the `glue' is community knowledge. We describe a theoretical basis and a practical representation framework on which community knowledge can be built and used. An illustrative example is given and further work noted.
Article
This article compares search effectiveness when using query-based Internet search (via the Google search engine), directory-based search (via Yahoo) and phrase-based query reformulation assisted search (via the Hyperindex browser) by means of a controlled, userbased experimental study. The focus was to evaluate aspects of the search process. Cognit...
Article
this paper, we don't consider the direction sensitivity of word pairs, and added the row and column vectors into one. Thus the dimension of each vector is reduced to vocabulary size n
Article
This article addresses these questions by articulating an evidential conceptual model of community synthesizing earlier definitions drawn from the literature and adding new conditions. It illustrates, by means of a small case study, how the level of community can be gauged based on evidence of core community conditions. The four conditions, purpose...
Chapter
Online community is having growing social and commercial impact on the WWW, but what does “community” mean online? Can the level of community be measured? This article articulates an evidential conceptual model of community synthesizing earlier definitions drawn from the literature and creating new core conditions. The four conditions, purpose, com...
Article
Full-text available
This article compares search effectiveness when using query-based Internet search (via the Google search engine), directory-based search (via Yahoo) and phrasebased query reformulation assisted search (via the Hyperindex browser) by means of a controlled, userbased experimental study. The focus was to evaluate aspects of the search process. Cogniti...
Article
Interactive query reformulation has been shown to promote effective retrieval. This paper addresses the problem of how to order candidate query refinements to facilitate effective perusal by the user. Several ordering strategies are discussed. A refinement ranking algorithm is proposed. Initial impressions gleaned from a web-based prototype are sha...
Article
This thesis is motivated by the desire to provide technological solutions to enhance human awareness in information processing tasks. The need is pressing. Paradoxically, as information piles up people become less and less aware due to perceived scarce cognitive resources. As a consequence, specialisations become ever more specialised, projects and...
Article
This paper describes part of a solution to the interpretation of human-readable policy documents into semi-automatic conformance checking. Using a socio-cognitively motivated representation of shared knowledge, and applying appropriate inference mechanisms from a normative perspective, a mechanism to automatically detect potentially non-conforming...

Citations

... In addition to these formal or semi-formal resources, communities often develop less tangible resources such as conventions of communication, roles, and identities [3] [4] [8] [9] [10] [15] [16] [19] [20] [23] [24] [25] [29] [30] [28] [34] [36] [41] [46] [47] [52] [53] [57]. We propose to have a secondary focus on these relatively intangible resources, because they are among the shared " goods " of the community, and they are essential to the functioning of the community. ...
... Despite its effectiveness, a lack of uptake has been one reason that IQE has not been as widely deployed in IR systems (Dennis et al., 1998). However, given this concern, there have been very few user studies that have considered this issue. ...
... As semantic space models are derived directly from an underlying corpus, the semantic representations of the words change accordingly. That is, the meaning of the words changes according how the company around them evolves [20]. As a consequence, the strength of semantic association between words varies as the corpus evolves. ...
... But, the real issue is that some of the most common search actions performed by searchers like term removal and addition are not properly supported by existing search features. Even in instances when they are used, there is significant cognitive workload involved in using them [8], and little guidance or indications to the kind of information they will retrieve is provided. ...
... The Dis sublogic is ultimately the province of agent X, as (s)he will ultimately chose those suggestions deemed worthy of discharge. Abductive systems computing associations from semantic space in the above fashion have been deployed in literature-based discovery [9] [3] [5], social network discovery in online communities [29] [30] [31] ...
... Before discussing the substantive topic, it behooves us to place a stake in the ground and outline our definition of online community. Our prior research [33] defines a conceptual model of online community identifying people and 'glue' as the primary components. The 'glue' is inter-group and inter-personal. ...
...  Discover implicit relationships among individuals in e-mail collections [8].  Detect anomalies in graphs of relationships [9]. ...
... Memetic primers also are potentially useful for providing new insights into both analyzing web discussions and forecasting trends in web communities. Interest in the examining discourse that happens in online spaces is increasing in both academia and industry1238]. This analysis provides a way to gauge the opinions of large, interested collectives of experts, in order to predict out-comes in various fields. ...
... The result was the creation of [5] or [17]). In keeping with previous research [24, 25, 28] 7. The sense-of-self vectors were projected onto the two axes of interest using simple vector algebra: each senseof-self vector for a blog feed in a day (vector of 1 x n) was projected onto the combined kin vector (1 x n) and the combined negative emotion vector (1 x n) yielding an x,y position against these two axes.Table 2 ...
... An unpublished internal paper, from which this section was developed, was created with equal authorship rights. A portion of it was taken slightly further and published in Song et al. [149] with myself having co-authorship and editorial input into the final paper, whose attribution should be equally shared among the four authors. Hence the work here is unpublished, but elements of it were performed in conjunction with work on the published paper. ...