Uncovering misconceptions through text analysis

Assessing students’ conceptual understanding of technical content is important for instructors as well as students to learn content and apply knowledge in various contexts. Concept inventories that identify possible misconceptions through validated multiple-choice questions are helpful in identifying a misconception that may exist, but do not provide a meaningful assessment of why they exist or the nature of the students’ understanding. We conducted a case study with undergraduate students in an electrical engineering course by testing a validated multiple-choice response concept inventory that we augmented with a component for students to provide written explanations for their multiple-choice selection. Results revealed that correctly chosen multiple-choice selections did not always match correct conceptual understanding for question testing a specific concept. The addition of a text-response to multiple-choice concept inventory questions provided an enhanced and meaningful assessment of students’ conceptual understanding and highlighted variables associated with current concept inventories or multiple choice questions.

Vanquishing the'Patent Trolls'

Patent law provides exclusive rights to exploit scientific inventions, which are novel, inventive, and useful. The regime is intended to promote innovation, investment in research and development, and access to scientific information. In recent times, there have been concerns that the patent system has been abused by opportunistic companies known by the phrase “patent trolls”. It has been alleged that such entities have stunted innovation and spurred unnecessary patent litigation. Adam Jaffe and Josh Lerner discuss such pathologies of patent law in their book, Innovation and Its Discontents: How our Broken Patent System is Endangering Innovation and Progress, and What To Do About It. James Bessen and Michael Meurer have addressed such concerns in their recent text, Patent Failure: How Judges, Bureaucrats, and Lawyers Put Innovators at Risk. There have been particular fears about the rise of “patent trolls” in the field of information technology. Peter Dekin, an assistant general counsel at Intel, used the phrase “patent troll” to describe firms, which acquired patents only to extract settlements from companies on dubious infringement claims.

Medical free-text to concept mapping as an information retrieval problem

Concept mapping involves determining relevant concepts from a free-text input, where concepts are defined in an external reference ontology. This is an important process that underpins many applications for clinical information reporting, derivation of phenotypic descriptions, and a number of state-of-the-art medical information retrieval methods. Concept mapping can be cast into an information retrieval (IR) problem: free-text mentions are treated as queries and concepts from a reference ontology as the documents to be indexed and retrieved. This paper presents an empirical investigation applying general-purpose IR techniques for concept mapping in the medical domain. A dataset used for evaluating medical information extraction is adapted to measure the effectiveness of the considered IR approaches. Standard IR approaches used here are contrasted with the effectiveness of two established benchmark methods specifically developed for medical concept mapping. The empirical findings show that the IR approaches are comparable with one benchmark method but well below the best benchmark.

Enhancement of relevant features for text mining

With the explosion of information resources, there is an imminent need to understand interesting text features or topics in massive text information. This thesis proposes a theoretical model to accurately weight specific text features, such as patterns and n-grams. The proposed model achieves impressive performance in two data collections, Reuters Corpus Volume 1 (RCV1) and Reuters 21578.

“Success in (Surviving) Bioscience and Pharmacology” – an eBook to improve the retention of diploma nurses transitioning to a Bachelor of Nursing course

Diploma students transitioning into the NS40 BNursing (BN) course at QUT withdraw from the bioscience and pharmacology units, and leave the university at higher rates than traditional students. The diploma students, entering in second year, have missed out on 2 units of bioscience taught to the traditional students in their first year, and miss out on a 3rd unit of bioscience taught to the traditional students in their 2nd year. Instead the diploma students receive one specialized unit in bioscience only i.e. a bridging unit. As a consequence, the diploma students may not have the depth of bioscience knowledge to be able to successfully study the bridging unit (LSB111) or the pharmacology unit (LSB384). Our plan was to write an eBook which refreshed and reinforced diploma students’ knowledge of bioscience aiming to prepare them with the concepts and terminology, and to build a level of confidence to support their transition to the BN. We have previously developed an intervention associated with reduced attrition of diploma nursing students, and this was our starting point. The study skills part of the initial intervention was addressed in the eBook, by links to the specialist services and resources available from our liaison librarian and academic skills adviser. The introductory bioscience/pharmacology information provided by the previous intervention involved material from standard textbooks. However, we considered this material too difficult for diploma students. Thus, we created simplified diagrams to go with text as part of our eBook. The outcome is an eBook, created and made available to the diploma students via the Community Website: “Surviving Bioscience and Pharmacology”. Using simplified diagrams to illustrate the concise text, definition to explain the concepts, the focus has been on encouraging self-awareness and help-seeking strategies and building students who take responsibility for their learning. All the nursing students in the second semester LSB384 Pharmacology Unit have been surveyed face-to-face to get feedback on their engagement with the eBook resource. The data has not been analysed to date. An important consideration is that the website be evaluated by the diploma students as they come into bioscience in first semester (LSB111), the student population for whom the eBook is primarily intended. To get a good response rate we need to do a face-to-face survey. However, we have not been able to do this, as the co-ordinator of the unit has changed since we started the project, and the present co-ordinator will not allow us access to these students.

Automatic ICD-10 classification of cancers from free-text death certificates

Objective Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates – an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. Methods Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. Results The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. Conclusion The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Mediation of improvements in sun protective and skin self-examination behaviours: Results from the healthy text study

Objective Melanoma is on the rise, especially in Caucasian populations exposed to high ultraviolet radiation such as in Australia. This paper examined the psychological components facilitating change in skin cancer prevention or early detection behaviours following a text message intervention. Methods The Queensland-based participants were 18 to 42 years old, from the Healthy Text study (N = 546). Overall, 512 (94%) participants completed the 12-month follow-up questionnaires. Following the social cognitive model, potential mediators of skin self-examination (SSE) and sun protection behaviour change were examined using stepwise logistic regression models. Results At 12-month follow-up, odds of performing an SSE in the past 12 months were mediated by baseline confidence in finding time to check skin (an outcome expectation), with a change in odds ratio of 11.9% in the SSE group versus the control group when including the mediator. Odds of greater than average sun protective habits index at 12-month follow-up were mediated by (a) an attempt to get a suntan at baseline (an outcome expectation) and (b) baseline sun protective habits index, with a change in odds ratio of 10.0% and 11.8%, respectively in the SSE group versus the control group. Conclusions Few of the suspected mediation pathways were confirmed with the exception of outcome expectations and past behaviours. Future intervention programmes could use alternative theoretical models to elucidate how improvements in health behaviours can optimally be facilitated.

vSpeak: Edge detection based feature extraction for sign to text conversion

This paper presents 'vSpeak', the first initiative taken in Pakistan for ICT enabled conversion of dynamic Sign Urdu gestures into natural language sentences. To realize this, vSpeak has adopted a novel approach for feature extraction using edge detection and image compression which gives input to the Artificial Neural Network that recognizes the gesture. This technique caters for the blurred images as well. The training and testing is currently being performed on a dataset of 200 patterns of 20 words from Sign Urdu with target accuracy of 90% and above.

Overview of the 2015 ALTA shared task: Identifying French cognates in English text

This paper presents an overview of the 6th ALTA shared task that ran in 2015. The task was to identify in English texts all the potential cognates from the perspective of the French language. In other words, identify all the words in the English text that would acceptably translate into a similar word in French. We present the motivations for the task, the description of the data and the results of the 4 participating teams. We discuss the results against a baseline and prior work.

Instagrammatics and digital methods: Studying visual social media, from selfies and GIFs to memes and emoji

Visual content is a critical component of everyday social media, on platforms explicitly framed around the visual (Instagram and Vine), on those offering a mix of text and images in myriad forms (Facebook, Twitter, and Tumblr), and in apps and profiles where visual presentation and provision of information are important considerations. However, despite being so prominent in forms such as selfies, looping media, infographics, memes, online videos, and more, sociocultural research into the visual as a central component of online communication has lagged behind the analysis of popular, predominantly text-driven social media. This paper underlines the increasing importance of visual elements to digital, social, and mobile media within everyday life, addressing the significant research gap in methods for tracking, analysing, and understanding visual social media as both image-based and intertextual content. In this paper, we build on our previous methodological considerations of Instagram in isolation to examine further questions, challenges, and benefits of studying visual social media more broadly, including methodological and ethical considerations. Our discussion is intended as a rallying cry and provocation for further research into visual (and textual and mixed) social media content, practices, and cultures, mindful of both the specificities of each form, but also, and importantly, the ongoing dialogues and interrelations between them as communication forms.