Learning domain-specific sentiment lexicons for predicting product sales

Generic sentiment lexicons have been widely used for sentiment analysis these days. However, manually constructing sentiment lexicons is very time-consuming and it may not be feasible for certain application domains where annotation expertise is not available. One contribution of this paper is the development of a statistical learning based computational method for the automatic construction of domain-specific sentiment lexicons to enhance cross-domain sentiment analysis. Our initial experiments show that the proposed methodology can automatically generate domain-specific sentiment lexicons which contribute to improve the effectiveness of opinion retrieval at the document level. Another contribution of our work is that we show the feasibility of applying the sentiment metric derived based on the automatically constructed sentiment lexicons to predict product sales of certain product categories. Our research contributes to the development of more effective sentiment analysis system to extract business intelligence from numerous opinionated expressions posted to the Web

A comparison of methods for classifying clinical samples based on proteomics data : a case study for statistical and machine learning approaches

The discovery of protein variation is an important strategy in disease diagnosis within the biological sciences. The current benchmark for elucidating information from multiple biological variables is the so called “omics” disciplines of the biological sciences. Such variability is uncovered by implementation of multivariable data mining techniques which come under two primary categories, machine learning strategies and statistical based approaches. Typically proteomic studies can produce hundreds or thousands of variables, p, per observation, n, depending on the analytical platform or method employed to generate the data. Many classification methods are limited by an n≪p constraint, and as such, require pre-treatment to reduce the dimensionality prior to classification. Recently machine learning techniques have gained popularity in the field for their ability to successfully classify unknown samples. One limitation of such methods is the lack of a functional model allowing meaningful interpretation of results in terms of the features used for classification. This is a problem that might be solved using a statistical model-based approach where not only is the importance of the individual protein explicit, they are combined into a readily interpretable classification rule without relying on a black box approach. Here we incorporate statistical dimension reduction techniques Partial Least Squares (PLS) and Principal Components Analysis (PCA) followed by both statistical and machine learning classification methods, and compared them to a popular machine learning technique, Support Vector Machines (SVM). Both PLS and SVM demonstrate strong utility for proteomic classification problems.

Learning communities learning series

In 2008 the introduction of the National Assessment Program – Literacy and Numeracy (NAPLAN), combined with the publication of the international comparative analyses of student achievement data (such as the Programme of International Student Assessment (PISA) developed by the Organisation for Economic Co-operation and Development (OECD) and the Trends in International Mathematics and Science Study (TIMSS) of the International Association for the Evaluation of Educational Achievement (IEA)) highlighted a significant priority for Australian education by identifying low levels of equity.

Contextualising learning for a real-world university: how an inverted curriculum in the first year can help better student retention

An identified issue within higher education is the high rates of student attrition after the first year, especially in the STEM disciplines. To address this issue, it is essential to reexamine and redesign the first year curriculum to engage and retain the students' interests while also scaffolding their learning experience. This session reports on an initiative based on the principles of the “inverted curriculum” within the Bachelor of Technology (BIT) course at the Queensland University of Technology (QUT) that began in 2009 and has resulted in a reduction in first-year attrition rates from 18% in 2008 to 10% in 2009 and 2010 despite a growth in student intake of 15% to 40% in the past two years. We present the process and methods that helped achieve this and initiate a discussion on the innovations that are possible within this concept of inverted curriculum and how it can be implemented.

Team teaching : working together to promote student learning

This book chapter examines the concept of team teaching from the perspective of the various stakeholders, in order to discuss the advantages and disadvantages of team teaching for students, to consider the positive and negative dimensions of collaborative teaching for teachers, and to review the implications for educational administration. In addition, attention will be paid to the issues associated with team teaching in the context of e-learning. The chapter concludes with a case study which discusses how the implementation of collaborative teaching within the library and information science discipline at an Australian university helped develop the authors’ understanding of socially constructed knowledge.

Building community resilience – learning from the 2011 floods in Southeast Queensland, Australia

The year 2010 was the wettest year on record for Queensland, Australia and the wettest year since 1974 for Southeast Queensland. The extremely heavy rain in early January 2011 fell on the catchments of heavily saturated Brisbane and Stanley Rivers systems resulting in significant runoff which rapidly produced a widespread and devastating flood event. The area of inundation was equivalent to the total land area of France and Germany combined. Over 200,000 people were affected leaving 35 people dead and 9 missing. The damage bill was estimated at over $1B and cost to the economy at over $10B with over 30,000 homes and 6,000 business flooded and 86 towns and regional centres affected. The need to disburse disaster funding in a prompt manner to the affected population was paramount to facilitate individuals getting their lives back to some normality. However, the payout of insurance claims has proved to be a major area of community anger. The ongoing impasse in payment of insurance compensation is attributed to the nature and number of claims, confusing definition of flooding and the lack or accuracy of information needed to determine individually the properties affected and legitimacy of claims. Information was not readily available at the micro-level including, extent and type of inundation, flood heights at property level and cause of damage. Events during the aftermath highlighted widespread community misconceptions concerning the technical factors associated with the flood event and the impact of such on access to legitimate compensation and assistance. Individual and community wide concerns and frustration, anger and depression, have arisen resulting from delays in the timely settlement of insurance claims. Lessons learnt during the aftermath are presented in the context of their importance as a basis for inculcating communities impacted by the flood event with resilience for the future.

Learning how to be responsive to public policy issues affecting SSSI members

Human survival depends on human ingenuity in using resources at hand to sustain human life. The historical record – in wrings and archaeological artefacts – provides evidence of the growth and collapse of political organisations and societies. In the institutions of Western civilisation, some traditions have endured over millennia where the roles of monarchs and public officials have been organised in perpetual succession. These roles were developed as conventions in the British Parliament after 1295 and provided the models of corporate governance in both public and private enterprise that have been continuously refined to the present day. In 2011, the Queensland Parliament legislated to introduce a new and more open system of scrutiny of legislation through a system of portfolio-based parliamentary committees. The committees began to function more actively in July 2012 and have inviting submissions from stakeholders and experts in a structured way to consider the government’s priorities in its legislative programme. The questions now are whether the Surveying and Spatial Sciences can respond expertly to address the terms of reference and meet the timetables of the various parliamentary committees. This paper discusses some of the more important and urgent issues that deserve debate that the profession needs to address in becoming more responsive to matters of public policy.

Reflection in Integrated Problem Based Learning : 20 years of continuing application to the teaching of architecture

In 1984 the School of Architecture and Built Environment within the University of Newcastle, Australia introduced an integrated program based on real design projects and using Integrated Problem Based Learning (IPBL) as the teaching method. Since 1984 there have been multiple changes arising from the expectations of the architectural fraternity, enrolling students, lecturers, available facilities, accreditation authorities and many others. These challenges have been successfully accommodated whilst maintaining the original purposes and principles of IPBL. The Architecture program has a combined two-degree structure consisting of a first degree, Bachelor of Science (Architecture), followed by a second degree, Bachelor of Architecture. The program is designed to simulate the problem-solving situations that face a working architect in every day practice. This paper will present the degree structure where each student is enrolled in a single course per semester incorporating design integration and study areas in design studies, professional studies, historical studies, technical studies, environmental studies and communication skills. Each year the design problems increase in complexity and duration set around an annual theme. With 20 years of successful delivery of any program there are highlights and challenges along the way and this paper will discuss some of the successes and barriers experienced within the School of Architecture and Built Environment in delivering IPBL. In addition, the reflective process investigates the currency of IPBL as an appropriate vehicle for delivering the curriculum in 2004 and any additional administrative or staff considerations required to enhance the continuing application of IPBL.

Learning to think spatially : what do students 'see' in numeracy test items?

Learning to think spatially in mathematics involves developing proficiency with graphics. This paper reports on 2 investigations of spatial thinking and graphics. The first investigation explored the importance of graphics as 1 of 3 communication systems (i.e. text, symbols, graphics) used to provide information in numeracy test items. The results showed that graphics were embedded in at least 50 % of test items across 3 year levels. The second investigation examined 11 – 12-year-olds’ performance on 2 mathematical tasks which required substantial interpretation of graphics and spatial thinking. The outcomes revealed that many students lacked proficiency in the basic spatial skills of visual memory and spatial perception and the more advanced skills of spatial orientation and spatial visualisation. This paper concludes with a reaffirmation of the importance of spatial thinking in mathematics and proposes ways to capitalize on graphics in learning to think spatially.

Connecting Indigenous stories with geology : inquiry-based learning in a middle years classroom

One way to integrate indigenous perspectives in junior science is through links between indigenous stories of the local area and science concepts. Using local indigenous stories about landforms, a teacher of year 8 students designed a unit on geology that catered for the diverse student population in his class. This paper reports on the inquiry-based approach structured around the requirements of the Australian Curriculum highlighting the learning and engagement of students during the unit.

Supporting the learning of rapid application development in a database environment

Intelligent Tutoring Systems (ITSs) are computer systems designed to provide individualised help to students, learning in a problem solving context. The difference between an ITS and a Computer Assisted Instruction (CAI) system is that an ITS has a Student Model which allows it to provide a better educational environment. The Student Model contains information on what the student knows, and does not know, about the domain being learnt, as well as other personal characteristics such as preferred learning style. This research has resulted in the design and development of a new ITS: Personal Access Tutor (PAT). PAT is an ITS that helps students to learn Rapid Application Development in a database environment. More specifically, PAT focuses on helping students to learn how to create forms and reports in Microsoft Access. To provide an augmented learning environment, PAT’s architecture is different to most other ITSs. Instead of having a simulation, PAT uses a widelyused database development environment (Microsoft Access). This enables the students to ask for help, while developing real applications using real database software. As part of this research, I designed and created the knowledge base required for PAT. This contains four models: the domain, student, tutoring and exercises models. The Instructional Expert I created for PAT provides individualised help to the students to help them correctly finish each exercise, and also proposes the next exercise that a student should work on. PAT was evaluated by students enrolled in the Databases subject at QUT, and by staff members involved in teaching the subject. The results of the evaluation were positive and are discussed in the thesis.

Enriching students’ intellectual diet through inquiry based learning

Traditionally, Science education has stressed the importance of teaching students to conduct ‘scientific inquiry’, with the main focus being the experimental model of inquiry used by real world scientists. Current educational approaches using constructivist pedagogy recognise the value of inquiry as a method for promoting the development of deep understanding of discipline content. A recent Information Learning Activity undertaken by a Grade Eight Science class was observed to discover how inquiry based learning is implemented in contemporary Science education. By analysing student responses to questionnaires and assessment task outcomes, the author was able to determine the level of inquiry inherent in the activity and how well the model supported student learning and the development of students’ information literacy skills. Although students achieved well overall, some recommendations are offered that may enable teachers to better exploit the learning opportunities provided by inquiry based learning. Planning interventions at key stages of the inquiry process can assist students to learn more effective strategies for dealing with cognitive and affective challenges. Allowing students greater input into the selection of topic or focus of the activity may encourage students to engage more deeply with the learning task. Students are likely to experience greater learning benefit from access to developmentally appropriate resources, increased time to explore topics and multiple opportunities to undertake information searches throughout the learning activity. Finally, increasing the cognitive challenge can enhance both the depth of students’ learning and their information literacy skills.

Examining preservice teachers’ applied learning experiences in the Teacher Education Done Differently (TEDD) project

Reviews have criticised universities for not embedding sufficient praxis for preparing preservice teachers for the profession. The Teacher Education Done Differently (TEDD) project explored praxis development for preservice teachers within existing university coursework. This mixed-method investigation involved an analysis of multiple case studies with preservice teacher involvement in university programs, namely: Ed Start for practicum I (n=26), III (n=23), and IV (n=12); Move It Use It (Health and Physical Education program; n=38), Studies of Society and its Environment (SOSE, n=24), and Science in Schools (n=38). The project included preservice teachers teaching primary students at the campus site in gifted education (the B-GR8 program, n=22). The percentage range for preservice teacher agreement of their praxis development leading up to practicum I, III, and IV was between 91-100% with a high mean score range (4.26-5.00). Other university units had similar findings except for SOSE (i.e., percentage range: 10-86%; M range: 2.33-4.00; SD range: 0.55-1.32). Qualitative data presented an understanding of the praxis development leading to the conclusion that additional applied learning experiences as lead-up days for field experiences and as avenues for exploring the teaching of specific subject areas presented opportunities for enhancing praxis.