Link discovery for Chinese/English cross-language web information retrieval

Nowadays people heavily rely on the Internet for information and knowledge. Wikipedia is an online multilingual encyclopaedia that contains a very large number of detailed articles covering most written languages. It is often considered to be a treasury of human knowledge. It includes extensive hypertext links between documents of the same language for easy navigation. However, the pages in different languages are rarely cross-linked except for direct equivalent pages on the same subject in different languages. This could pose serious difficulties to users seeking information or knowledge from different lingual sources, or where there is no equivalent page in one language or another. In this thesis, a new information retrieval task—cross-lingual link discovery (CLLD) is proposed to tackle the problem of the lack of cross-lingual anchored links in a knowledge base such as Wikipedia. In contrast to traditional information retrieval tasks, cross language link discovery algorithms actively recommend a set of meaningful anchors in a source document and establish links to documents in an alternative language. In other words, cross-lingual link discovery is a way of automatically finding hypertext links between documents in different languages, which is particularly helpful for knowledge discovery in different language domains. This study is specifically focused on Chinese / English link discovery (C/ELD). Chinese / English link discovery is a special case of cross-lingual link discovery task. It involves tasks including natural language processing (NLP), cross-lingual information retrieval (CLIR) and cross-lingual link discovery. To justify the effectiveness of CLLD, a standard evaluation framework is also proposed. The evaluation framework includes topics, document collections, a gold standard dataset, evaluation metrics, and toolkits for run pooling, link assessment and system evaluation. With the evaluation framework, performance of CLLD approaches and systems can be quantified. This thesis contributes to the research on natural language processing and cross-lingual information retrieval in CLLD: 1) a new simple, but effective Chinese segmentation method, n-gram mutual information, is presented for determining the boundaries of Chinese text; 2) a voting mechanism of name entity translation is demonstrated for achieving a high precision of English / Chinese machine translation; 3) a link mining approach that mines the existing link structure for anchor probabilities achieves encouraging results in suggesting cross-lingual Chinese / English links in Wikipedia. This approach was examined in the experiments for better, automatic generation of cross-lingual links that were carried out as part of the study. The overall major contribution of this thesis is the provision of a standard evaluation framework for cross-lingual link discovery research. It is important in CLLD evaluation to have this framework which helps in benchmarking the performance of various CLLD systems and in identifying good CLLD realisation approaches. The evaluation methods and the evaluation framework described in this thesis have been utilised to quantify the system performance in the NTCIR-9 Crosslink task which is the first information retrieval track of this kind.

Modelling users' contextual querying behaviour for web image searching

The rapid growth of visual information on Web has led to immense interest in multimedia information retrieval (MIR). While advancement in MIR systems has achieved some success in specific domains, particularly the content-based approaches, general Web users still struggle to find the images they want. Despite the success in content-based object recognition or concept extraction, the major problem in current Web image searching remains in the querying process. Since most online users only express their needs in semantic terms or objects, systems that utilize visual features (e.g., color or texture) to search images create a semantic gap which hinders general users from fully expressing their needs. In addition, query-by-example (QBE) retrieval imposes extra obstacles for exploratory search because users may not always have the representative image at hand or in mind when starting a search (i.e. the page zero problem). As a result, the majority of current online image search engines (e.g., Google, Yahoo, and Flickr) still primarily use textual queries to search. The problem with query-based retrieval systems is that they only capture users’ information need in terms of formal queries;; the implicit and abstract parts of users’ information needs are inevitably overlooked. Hence, users often struggle to formulate queries that best represent their needs, and some compromises have to be made. Studies of Web search logs suggest that multimedia searches are more difficult than textual Web searches, and Web image searching is the most difficult compared to video or audio searches. Hence, online users need to put in more effort when searching multimedia contents, especially for image searches. Most interactions in Web image searching occur during query reformulation. While log analysis provides intriguing views on how the majority of users search, their search needs or motivations are ultimately neglected. User studies on image searching have attempted to understand users’ search contexts in terms of users’ background (e.g., knowledge, profession, motivation for search and task types) and the search outcomes (e.g., use of retrieved images, search performance). However, these studies typically focused on particular domains with a selective group of professional users. General users’ Web image searching contexts and behaviors are little understood although they represent the majority of online image searching activities nowadays. We argue that only by understanding Web image users’ contexts can the current Web search engines further improve their usefulness and provide more efficient searches. In order to understand users’ search contexts, a user study was conducted based on university students’ Web image searching in News, Travel, and commercial Product domains. The three search domains were deliberately chosen to reflect image users’ interests in people, time, event, location, and objects. We investigated participants’ Web image searching behavior, with the focus on query reformulation and search strategies. Participants’ search contexts such as their search background, motivation for search, and search outcomes were gathered by questionnaires. The searching activity was recorded with participants’ think aloud data for analyzing significant search patterns. The relationships between participants’ search contexts and corresponding search strategies were discovered by Grounded Theory approach. Our key findings include the following aspects: - Effects of users' interactive intents on query reformulation patterns and search strategies - Effects of task domain on task specificity and task difficulty, as well as on some specific searching behaviors - Effects of searching experience on result expansion strategies A contextual image searching model was constructed based on these findings. The model helped us understand Web image searching from user perspective, and introduced a context-aware searching paradigm for current retrieval systems. A query recommendation tool was also developed to demonstrate how users’ query reformulation contexts can potentially contribute to more efficient searching.

Protecting web 2.0 services from botnet exploitations

Recently, botnet, a network of compromised computers, has been recognized as the biggest threat to the Internet. The bots in a botnet communicate with the botnet owner via a communication channel called Command and Control (C & C) channel. There are three main C & C channels: Internet Relay Chat (IRC), Peer-to-Peer (P2P) and web-based protocols. By exploiting the flexibility of the Web 2.0 technology, the web-based botnet has reached a new level of sophistication. In August 2009, such botnet was found on Twitter, one of the most popular Web 2.0 services. In this paper, we will describe a new type of botnet that uses Web 2.0 service as a C & C channel and a temporary storage for their stolen information. We will then propose a novel approach to thwart this type of attack. Our method applies a unique identifier of the computer, an encryption algorithm with session keys and a CAPTCHA verification.

Development of Mobile Web App "ESP" for DeepBlue to interrogate how an audience is thinking

DeepBlue is much more than just an orchestra. Their innovative approach to audience engagement led it to develop ESP, their Electronic Show Programme web app which allows for real-time (synchronous) and delayed (asynchronous) audience interaction, customer feedback and research. The show itself is driven invisibly by a music technology operating system (currently QUT's Yodel) that allows them to adapt to a wide range of performance venues and varied types of presentation. DeepBlue's community engagement program has enabled over 5,500 young musicians and community choristers to participate in professional productions, it is also a cornerstone of DeepBlue's successful business model. You can view the ESP mobile web app at m.deepblue.net.au if you view this and only the landing page is active, there is not a show taking place or imminent. ESP prototype has already been used for 18 months. Imagine knowing what your audience really thinks – in real time so you can track their feelings and thoughts through the show. This tool has been developed and used by the performing group DeepBlue since late 2012 in Australia and Asia (even translated into Vietnamese). It has mostly superseded DeepBlue's SMS realtime communication during a show. It enables an event presenter or performance group to take the pulse of an audience through a series of targeted questions that can be anonymous or attributed. This will help build better, long-lasting, and more meaningful relationships with groups and individuals in the community. This can take place on a tablet, mobile phone or future platforms. There are three organisations trialling it so far.

A dynamic Web agent for verifying the security and integrity of a Web site's contents

To harness safe operation of Web-based systems in Web environments, we propose an SSPA (Server-based SHA-1 Page-digest Algorithm) to verify the integrity of Web contents before the server issues an HTTP response to a user request. In addition to standard security measures, our Java implementation of the SSPA, which is called the Dynamic Security Surveillance Agent (DSSA), provides further security in terms of content integrity to Web-based systems. Its function is to prevent the display of Web contents that have been altered through the malicious acts of attackers and intruders on client machines. This is to protect the reputation of organisations from cyber-attacks and to ensure the safe operation of Web systems by dynamically monitoring the integrity of a Web site's content on demand. We discuss our findings in terms of the applicability and practicality of the proposed system. We also discuss its time metrics, specifically in relation to its computational overhead at the Web server, as well as the overall latency from the clients' point of view, using different Internet access methods. The SSPA, our DSSA implementation, some experimental results and related work are all discussed

The OnTrack Diabetes web-based program for type 2 diabetes and dysphoria self-management: A randomized controlled trial protocol

Background: The prevalence of type 2 diabetes is rising with the majority of patients practicing inadequate disease self-management. Depression, anxiety, and diabetes-specific distress present motivational challenges to adequate self-care. Health systems globally struggle to deliver routine services that are accessible to the entire population, in particular in rural areas. Web-based diabetes self-management interventions can provide frequent, accessible support regardless of time and location Objective: This paper describes the protocol of an Australian national randomized controlled trial (RCT) of the OnTrack Diabetes program, an automated, interactive, self-guided Web program aimed to improve glycemic control, diabetes self-care, and dysphoria symptoms in type 2 diabetes patients. Methods: A small pilot trial is conducted that primarily tests program functionality, efficacy, and user acceptability and satisfaction. This is followed by the main RCT, which compares 3 treatments: (1) delayed program access: usual diabetes care for 3 months postbaseline followed by access to the full OnTrack Diabetes program; (2) immediate program: full access to the self-guided program from baseline onward; and (3) immediate program plus therapist support via Functional Imagery Training (FIT). Measures are administered at baseline and at 3, 6, and 12 months postbaseline. Primary outcomes are diabetes self-care behaviors (physical activity participation, diet, medication adherence, and blood glucose monitoring), glycated hemoglobin A1c (HbA1c) level, and diabetes-specific distress. Secondary outcomes are depression, anxiety, self-efficacy and adherence, and quality of life. Exposure data in terms of program uptake, use, time on each page, and program completion, as well as implementation feasibility will be conducted. Results: This trial is currently underway with funding support from the Wesley Research Institute in Brisbane, Australia. Conclusions: This is the first known trial of an automated, self-guided, Web-based support program that uses a holistic approach in targeting both type 2 diabetes self-management and dysphoria. Findings will inform the feasibility of implementing such a program on an ongoing basis, including in rural and regional locations.

PM348 Heart education assessment and rehabilitation toolkit: Heart online. A web resource for clinicians

Access to the right information at the right time is a challenge facing health professionals across the globe. HEART Online (www.heartonline.org.au) is a website designed to support the delivery of evidence based care for the prevention and rehabilitation of heart disease. It was developed by the Queensland Government and the National Heart Foundation of Australia and launched May 2013.

Doing Digital Composition on the Social Web: Knowledge Processes in Literacy Learning

The power to influence others in ever-expanding social networks in the new knowledge economy is tied to capabilities with digital media production. This chapter draws on research in elementary classrooms to examine the repertoires of cross-disciplinary knowledge that literacy learners need to produce innovative digital media via the “social web”. It focuses on the knowledge processes that occurred when elementary students engaged in multimodal text production with new digital media. It draws on Kalantzis and Cope’s (2008) heuristic for theorizing “Knowledge Processes” in the Learning by Design approach to pedagogy. Learners demonstrate eight “Knowledge Processes” across different subject domains, skills areas, and sensibilities. Drawing data from media-based lessons across several classroom and schools, this chapter examines what kinds of knowledge students utilize when they produce digital, multimodal texts in the classroom. The Learning by Design framework is used as an analytic tool to theorize how students learn when they engaged in a specific domain of learning – digital media production.

Cover page of a binder for maps of Crimea and Ukraine

Digital image

Cover page of a binder for plans of tracts of land on Crimea

Digital image

A Novel Multimodal Interface for Improving Visually Impaired People's Web Accessibility

This paper introduces a novel interface designed to help blind and visually impaired people to explore and navigate on the Web. In contrast to traditionally used assistive tools, such as screen readers and magnifiers, the new interface employs a combination of both audio and haptic features to provide spatial and navigational information to users. The haptic features are presented via a low-cost force feedback mouse allowing blind people to interact with the Web, in a similar fashion to their sighted counterparts. The audio provides navigational and textual information through the use of non-speech sounds and synthesised speech. Interacting with the multimodal interface offers a novel experience to target users, especially to those with total blindness. A series of experiments have been conducted to ascertain the usability of the interface and compare its performance to that of a traditional screen reader. Results have shown the advantages that the new multimodal interface offers blind and visually impaired people. This includes the enhanced perception of the spatial layout of Web pages, and navigation towards elements on a page. Certain issues regarding the design of the haptic and audio features raised in the evaluation are discussed and presented in terms of recommendations for future work.

Visually extracting data records from the deep web

Web sites that rely on databases for their content are now ubiquitous. Query result pages are dynamically generated from these databases in response to user-submitted queries. Automatically extracting structured data from query result pages is a challenging problem, as the structure of the data is not explicitly represented. While humans have shown good intuition in visually understanding data records on a query result page as displayed by a web browser, no existing approach to data record extraction has made full use of this intuition. We propose a novel approach, in which we make use of the common sources of evidence that humans use to understand data records on a displayed query result page. These include structural regularity, and visual and content similarity between data records displayed on a query result page. Based on these observations we propose new techniques that can identify each data record individually, while ignoring noise items, such as navigation bars and adverts. We have implemented these techniques in a software prototype, rExtractor, and tested it using two datasets. Our experimental results show that our approach achieves significantly higher accuracy than previous approaches. Furthermore, it establishes the case for use of vision-based algorithms in the context of data extraction from web sites.

Web Psychosocial Surveys in Cancer Survivorship— A Methodological Note

The number of Internet surveys is increasing, and there is a need to examine critically their value in psychosocial cancer care research. This study explored the use of an online method of recruiting and surveying people affected by cancer. An online survey was designed to measure the health status and service needs of adult cancer survivors and caregivers. The online survey received 491 page visits; only 5% of visitors (13 survivors and 14 cancer caregivers) completed the online questionnaire. The average age of survivors and caregivers was 43 and 42 years, respectively. The majority of survivor and caregiver online respondents were female (23/27, 85%) and had been affected by cancer between 1 and 3 years previously (16/27, 59%). Our online research did not appear to be an effective method for recruiting and surveying the psychosocial health of cancer survivors. This study identified potential pitfalls and obstacles of online cancer care surveys particularly in relation to the age of cancer survivors, access to the Internet and the need to ensure surveys are easily and immediately accessible. Future Internet surveys should pay particular attention to the need to advertise and improve survey access via targeted and tailored techniques.

Suporte a testes automáticos em aplicações web geradas com a OutSystems Platform

Dissertação de natureza científica para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Credibility on the Web

"La nature flexible et interactive d’Internet implique que de plus en plus de consommateurs l’utilisent en tant qu’outil d’information sur tous les sujets imaginables, qu’il s’agisse de trouver la meilleurs aubaine sur un billet d’avion, ou de se renseigner sur certains problèmes liés à leur santé. Cependant, une grande quantité de l’information disponible en ligne n’est pas impartiale. Certains sites web ne présentent qu’une vision des choses ou font la promotion des produits d’une seule entreprise. Les consommateurs sont plus habitués à évaluer le poid à attribuer à certains conseils ou autres formes d’informations dans un contexte différent. Une telle évaluation de la crédibilité d’une information devient plus difficile dans le monde virtuel où les indices du monde réel, de l’écrit ou de l’interaction face-à-face sont absents. Consumers International a développé une définition de la notion de « crédibilité de l’information retrouvée en ligne » et a établi une liste de critères pouvant l’évaluer. Entre les mois d’avril et juillet 2002, une équipe représentant 13 pays a visité 460 sites web destinés à fournir de l’information sur la santé, sur des produits financiers et sur les prix de voyages et de différents biens de consommation en utilisant ces critères. L’appréciation de ces données nous démontre que les consommateurs doivent faire preuve de prudence lorsqu’ils utilisent Internet comme source d’information. Afin de faire des choix éclairés sur la valeur à donner à une information retrouvée en ligne, les consommateurs doivent connaître ce qui suit : L’identité du propriétaire d’un site web, ses partenaires et publicitaires; La qualité de l’information fournie, incluant son actualité et sa clarté, l’identité des sources citées et l’autorité des individus donnant leur opinion; Si le contenu du site est contrôlé par des intérêts commerciaux, ou, s’il offre des liens, la nature de la relation avec le site visé; et Si on lui demandera de fournir des données personnelles, l’usage réservé à ces données et les mesures employées pour protéger ces données. Cette étude démontre que plusieurs sites ne fournissent pas suffisamment de détails dans ces domaines, ce qui risque d’exposer le consommateur à des informations inexactes, incomplètes ou même délibérément fausses. Les discours exagérés ou vagues de certains sites concernant leurs services ne fait qu’ajouter à la confusion. Ceci peut résulter en une perte de temps ou d’argent pour le consommateur, mais pour certaines catégories d’informations, comme les conseils visant la santé, le fait de se fier à de mauvais conseils peut avoir des conséquences beaucoup plus graves. Cette étude vise à aviser les consommateurs de toujours vérifier le contexte des sites avant de se fier aux informations qui s’y retrouvent. Elle demande aux entreprises d’adopter de meilleures pratiques commerciales et de fournir une information plus transparente afin d’accroître la confiance des consommateurs. Elle demande finalement aux gouvernements de contribuer à ce mouvement en assurant le respect des lois relatives à la consommation et des standards existants tant dans le monde réel que dans le monde virtuel."