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

Teaching and assessing critical thinking : the interaction of student approaches to learning and teaching approaches

This study explored the relationship among student approaches to learning and teaching methods on critical thinking in two business units. Key findings included differences in critical thinking scores between student approaches to learning and some evidence of an interaction between student approaches to learning and critical thinking teach method (immersion vs. infusion). Possible explanations for the results are examined and implications for developing critical thinking skills across a degree discussed. What is apparent is that as Universities move towards program-wide level assessment of critical thinking, further work is required in terms of the design of critical thinking teaching interventions and assessment at the unit, school, and degree level. The session will discuss the challenges in developing critical thinking programs in individual units and at the Faculty level.

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.

Australian higher education evaluation through assurance of learning

A collaborative research project conducted by five Australian universities inquired into the philosophy and motivation for Assurance of Learning (AoL) as a process of education evaluation. Associate Deans Teaching and Learning representing Business schools from twenty-five universities across Australia participated in telephone interviews. Data was analysed using NVIVO9. Results indicated that articulated rationale for AoL was both ensuring that students had acquired the attributes and skills the universities claimed they had, and the philosophy of continuous improvement. AoL was motivated both by ritualistic objectives to satisfy accreditation requirements and virtuous agendas for quality improvement. Closing-the-loop was emphasised, but was mostly wishful thinking for next steps beyond data collection and reporting. AoL was conceptualised as one element within the larger context of quality review, but there was no evidence of comprehensive frameworks or strategic plans.

Assurance of learning – are academics and senior management singing from the same hymn sheet?

Assurance of learning (AoL) is an important process in quality education, designed to measure the accomplishment of educational aims at the core of an institution’s programs, whilst encouraging faculty to continuously develop and improve the programs and courses. This paper reports on a study of Australian business schools to investigate current AoL practices through semi structured interviews with senior faculty leaders followed by focus group interviews with groups of senior program leaders and groups of academic teaching staff. Initial findings indicate there are significant challenges in encouraging academic staff to commit to the process and recognise the benefits of assuring learning. The differences in understanding between the various leaders and the academics were highlighted through the different focus groups. Leaders’ stressed strategic issues such as staff engagement and change, while academics focussed on process issues such as teaching graduate attributes and external accreditation. Understanding the differences in the perspectives of leaders and faculty is important, as without a shared understanding between the two groups, there is likely to be limited engagement, which creates difficulties in developing effective assurance of learning processes. Findings indicate that successful strategies developed to foster shared values on assurance of learning include: strong senior leaders’ commitment; developing champions among program and unit level staff; providing professional development opportunities; promoting and celebrating success and effectiveness; and ensuring an inclusive process with academics of all levels collaborating in the development and implementation of the process.