Content analysis of e-petitions with topic modeling: How to train and evaluate LDA models?

E-petitions have become a popular vehicle for political activism, but studying them has been difficult because efficient methods for analyzing their content are currently lacking. Researchers have used topic modeling for content analysis, but current practices carry some serious limitations. While modeling may be more efficient than manually reading each petition, it generally relies on unsupervised machine learning and so requires a dependable training and validation process. And so this paper describes a framework to train and validate Latent Dirichlet Allocation (LDA), the simplest and most popular topic modeling algorithm, using e-petition data. With rigorous training and evaluation, 87% of LDA-generated topics made sense to human judges. Topics also aligned well with results from an independent content analysis by the Pew Research Center, and were strongly associated with corresponding social events. Computer-assisted content analysts can benefit from our guidelines to supervise every process of training and evaluation of LDA. Software developers can benefit from learning the demands of social scientists when using LDA for content analysis. These findings have significant implications for developing LDA tools and assuring validity and interpretability of LDA content analysis. In addition, LDA topics can have some advantages over subjects extracted by manual content analysis by reflecting multiple themes expressed in texts, by extracting new themes that are not highlighted by human coders, and by being less prone to human bias.     

BOOK REVIEWS

FIFTY YEARS OF AMERICAN EDUCATION A HISTORICAL REVIEW AND CRITICAL APPRAISAL. By Edgar W. Knight.
ROADS TO AGREEMENT: SUCCESSFUL METHODS IN THE SCIENCE OF HUMAN RELATIONS. By Stuart Chase, in collaboration with Marian Tyler Chase.     

Investigation of the WISC-R for use with retarded children: Correlation with the 1972 Stanford-Binet and comparison of WISC and WISC-R profiles

A group of 80 mentally retarded youngsters, aged 6 to 16, was tested on the WISC-R, primarily to assess the continuity of measurement between the old and new WISCs. The WISC-R IQs correlated .65 to .82 with Stanford-Binet IQ for a subsample of 45 children, resembling the coefficients between the 1949 WISC and the Binet for retarded groups. In addition, the WISC-R test profiles for the 80 children corresponded closely to the WISC test profiles for many retarded samples. Thus, there was evidence to support the continuity of the WISC-R with its predecessor for retarded populations.     

Academic vocabulary and reading comprehension: exploring the relationships across measures of vocabulary knowledge

Reading and Writing - This study examined the relationship between knowledge of academic vocabulary and reading comprehension in data contributed by 5855 middle school students. Each student...     

Toward harmonious East–West educational partnerships: a study of cultural differences between Taiwanese and Norwegian engineering students

The collaboration activities between educational institutions in the East and the West are on the increase as an increasingly globalized economy requires graduates to have the skills to work across cultural divides. Such collaborations are difficult and require patience. One challenge is that students or teachers may have misconceptions about aspects of the other culture that may cause problems. This study sets out to identify what values students in typical Eastern and Western societies associate with a good student, good student behavior, good teachers and good lectures with the purpose to identify discrepancies. This study is based on the results of a pair-wise ranking questionnaire completed by 233 Taiwanese and Norwegian students of both engineering and non-technical subjects. The results confirm some established beliefs regarding culturally related differences. However, several issues were found to be culturally neutral, and cultural differences were identified for several issues that were predicted to be culturally neutral. The results of this study may be useful to educators involved in East–West internationalization.     

Understanding pupils' hiding techniques in physical education

Previous research shows that some pupils find physical education (PE) demanding and difficult. Some pupils use strategies to avoid participation in PE when it is demanding and difficult. The present study aims to illuminate and describe strategies used by pupils to avoid negative self-perception in difficult situations and activities in PE classes. This behavior, called hiding techniques, arises out of the need to protect self-perception and save academic or social face in the PE subject. Interviews and focus groups have been used with six PE teachers in Norwegian primary and lower secondary school to illuminate hiding techniques. Ten former pupils have also been interviewed about their experience of PE classes in primary/lower secondary school and upper secondary school for the same purpose. The results show that hiding techniques are experienced and practised in many different ways, and that there is a wide range of causes behind hiding techniques. Pupils' hiding techniques are categorized into main types, and the causes underlying the hiding techniques are summarized. This study provides insight into educational challenges that need to be highlighted to help all pupils in school, not just those who complete the PE subject without any real problems, to realize an important aim of the subject and to experience the joy of movement and lasting physical activity. It also highlights hiding techniques that are sophisticated, clever and deliberate actions pupils use to take control over the social setting in PE through the covert act of resistance rather than passively allowing the oppressive social setting to overpower them.     

Internet Resources for Middle School Science: Golden Opportunity or “Silicon Snake Oil”?

This study examines the experiences of six teachers at three schools in learning about and beginning to implement or enhance project-based learning in their middle school science classrooms using a variety of resources available through the Internet. Data were gathered over a one-year period ending in March, 1996. As a result of their experience, teachers became aware of the possibilities and the problems created by both the nearly unlimited quantity of information available on the Internet and the limited quality and relevance of much of that information. Positive and negative experiences described by teachers and the variety of issues and concerns which they reflect are compared and contrasted, including: unreliability of network connections; potential availability to students of inappropriate resources; consistency of classroom organization structures necessary to facilitate Internet access with normally preferred teaching methods; the dependence of the efficiency and motivational value of project-based units on students' appreciation of the nature and power of the technology; conflict between curriculum space devoted to teaching about technology and that devoted to substantively using the technology to teach about science and related subjects; the on call convenience of the Internet; the up-to-date nature of much of the scientific information available on the Internet; Internet-based information (versus textbook information) as authoritative yet not impersonal.