Automatic thematic classification of election manifestos

We digitized three years of Dutch election manifestos annotated by the Dutch political scientist Isaac Lipschits. We used these data to train a classifier that can automatically label new, unseen election manifestos with themes. Having the manifestos in a uniform XML format with all paragraphs annotated with their themes has advantages for both electronic publishing of the data and diachronic comparative data analysis. The data that we created will be disclosed to the public through a search interface. This means that it will be possible to query the data and filter them on themes and parties. We optimized the Lipschits classifier on the task of classifying election manifestos using models trained on earlier years. We built a classifier that is suited for classifying election manifestos from 2002 onwards using the data from the 1980s and 1990s. We evaluated the results by having a domain expert manually assess a sample of the classified data. We found that our automatic classifier obtains the same precision as a human classifier on unseen data. Its recall could be improved by extending the set of themes with newly emerged themes. Thus when using old political texts to classify new texts, work is needed to link and expand the set of themes to newer topics.     

Key phrase aware transformer for abstractive summarization

Abstractive summarization aims to generate a concise summary covering salient content from single or multiple text documents. Many recent abstractive summarization methods are built on the transformer model to capture long-range dependencies in the input text and achieve parallelization. In the transformer encoder, calculating attention weights is a crucial step for encoding input documents. Input documents usually contain some key phrases conveying salient information, and it is important to encode these phrases completely. However, existing transformer-based summarization works did not consider key phrases in input when determining attention weights. Consequently, some of the tokens within key phrases only receive small attention weights, which is not conducive to encoding the semantic information of input documents. In this paper, we introduce some prior knowledge of key phrases into the transformer-based summarization model and guide the model to encode key phrases. For the contextual representation of each token in the key phrase, we assume the tokens within the same key phrase make larger contributions compared with other tokens in the input sequence. Based on this assumption, we propose the Key Phrase Aware Transformer (KPAT), a model with the highlighting mechanism in the encoder to assign greater attention weights for tokens within key phrases. Specifically, we first extract key phrases from the input document and score the phrases’ importance. Then we build the block diagonal highlighting matrix to indicate these phrases’ importance scores and positions. To combine self-attention weights with key phrases’ importance scores, we design two structures of highlighting attention for each head and the multi-head highlighting attention. Experimental results on two datasets (Multi-News and PubMed) from different summarization tasks and domains show that our KPAT model significantly outperforms advanced summarization baselines. We conduct more experiments to analyze the impact of each part of our model on the summarization performance and verify the effectiveness of our proposed highlighting mechanism.     

Competing priorities: Singaporean teachers’ perspectives on critical literacy

This paper explores a group of Singaporean English language teachers’ knowledge and beliefs about critical literacy as well as their perspectives on how best to teach literacy and critical literacy in Singapore schools. A face-to-face survey was conducted among 58 English language teachers by using open-ended questions. The survey covered various topics related to literacy instruction including text decoding, meaning construction, and critical analysis of texts. The participating teachers believed strongly that reading and writing are transactional and interactional practices. However, they were less certain in their beliefs about teaching critical literacy including the critical, analytical and evaluative aspects of text reading. Some teachers saw a conflict between using time on teaching critical literacy and preparing students to pass their exams. As critical literacy is not a requirement at exams, they found it difficult to justify using time teaching it. The results suggest that the teachers’ belief systems are strongly influenced by the broad macro-structure of the educational system in Singapore and their own educational experiences.     

文本阐释原理与文献传播研究

文本阐释原理与文献传播研究●周庆山ＡＢＳＴＲＡＣＴＴｈｅｔｈｅｏｒｙｏｆｔｅｘｔｅｘｐｌａｎｎａｔｉｏｎｉｓｐｕｔｆｏｒｗａｒｄｗｈｉｌｅａｎａｌｙｚｉｎｇｔｈｅｓｉｇｎｉｆｉｃａｎｃｅｏｆｔｅｘｔｅｘｐｌａｎａｔｉｏｎｉｎｔｈｅｓｔｕｄｙｏｆｄｏｃ...     

Sports-based Text Sets: Fostering Critical Literacy at the Intersections of Sport and Society

Sports culture is central to the lives of many students, whether they participate in athletic competitions or sports fandom. Unfortunately, sports culture also reflects many sociopolitical issues and inequities that impinge upon our greater society in the present day (e.g., domestic violence, racism). For those reasons, sports-based text sets—diverse collections of texts about figures, events, and happenings in sports culture—stand to support teachers in honoring students' knowledge of and interests in sports culture while also facilitating critical literacy practices through the investigation of inequities that ail both sport and society. This article introduces the notion of a sports-based text set, addresses the types of texts that might be featured in such a set, and presents ideas for exploring specific texts with students, using the issue of inequitable compensation for male and female athletes as an example.     

Using log variables in a learning management system to evaluate learning activity using the lens of activity theory

As the advance of learning technologies and analytics tools continues, learning management systems (LMSs) have been required to fulfil the growing expectations for smart learning. However, the reality regarding the level of technology integration in higher education differs considerably from such expectations or the speed of advances in educational technologies. This research aimed to evaluate the current activation levels and usage patterns of a LMS. A large data-set was analysed, which included the online activity information from 7940 courses. Through data pre-processing, general indicators reflecting login frequencies of the virtual campus and activity-based indicators presenting the activation patterns of diverse functions provided by Moodle were derived. Activity theory was applied to interpret the results of analysis, since it has been recognised as a powerful framework to understand phenomena encompassing interactive systems. Further, time-series investigation over three consecutive semesters allowed observation of historical changes. The results revealed considerably low use of the virtual campus with only slight changes, as well as significantly different activity patterns across course attributes and colleges. Contradictions among components in the activity system are discussed, along with the implications for improving teaching and learning with LMS in higher education.     

WebIntera-classroom: an interaction-aware virtual learning environment for augmenting learning interactions

Interaction is critical for successful teaching and learning in a virtual learning environment (VLE). This paper presents a web-based interaction-aware VLE – WebIntera-classroom – which aims to augment learning interactions by increasing the learner-to-content and learner-to-instructor interactions. We design a ubiquitous interactive interface that integrates a pen-and-paper interface with a web-based whiteboard to promote effective learner-to-content interactions. We develop a learning analytics tool that instantly shows learners’ learning interactions, with which instructors can supervise learner-to-instructor interactions. We implement a high-granularity Learning Analytics Engine (hgLAE) to broadcast, record and play a lecture recording. The hgLAE identifies hotspots in a lecture recording and raises students’ awareness of the hotspots when they watch the recording. WebIntera-classroom has been deployed in 11 universities in China. The system obtained high satisfaction in the questionnaires (N?=?464) and face-to-face interviews (N?=?60) conducted with the users from China Jiliang University. We compared the students’ performance, respectively, achieved in traditional classroom and in WebIntera-classroom at China Jiliang University during 2012–2013. The result demonstrates that the students could gain performance improvement by using WebIntera-classroom.     

Efficient implementation of associative classifiers for document classification

In practical text classification tasks, the ability to interpret the classification result is as important as the ability to classify exactly. Associative classifiers have many favorable characteristics such as rapid training, good classification accuracy, and excellent interpretation. However, associative classifiers also have some obstacles to overcome when they are applied in the area of text classification. The target text collection generally has a very high dimension, thus the training process might take a very long time. We propose a feature selection based on the mutual information between the word and class variables to reduce the space dimension of the associative classifiers. In addition, the training process of the associative classifier produces a huge amount of classification rules, which makes the prediction with a new document ineffective. We resolve this by introducing a new efficient method for storing and pruning classification rules. This method can also be used when predicting a test document. Experimental results using the 20-newsgroups dataset show many benefits of the associative classification in both training and predicting when applied to a real world problem.     

Topic discovery based on text mining techniques

In this paper, we present a topic discovery system aimed to reveal the implicit knowledge present in news streams. This knowledge is expressed as a hierarchy of topic/subtopics, where each topic contains the set of documents that are related to it and a summary extracted from these documents. Summaries so built are useful to browse and select topics of interest from the generated hierarchies. Our proposal consists of a new incremental hierarchical clustering algorithm, which combines both partitional and agglomerative approaches, taking the main benefits from them. Finally, a new summarization method based on Testor Theory has been proposed to build the topic summaries. Experimental results in the TDT2 collection demonstrate its usefulness and effectiveness not only as a topic detection system, but also as a classification and summarization tool.     

‘Do you want me to translate this in English or in a better Mandinka language?’: Unequal literacy regimes and grassroots spelling practices in peri-urban Gambia

This paper presents a comparative ethnographic analysis of two versions of a grassroots text in Mandinka language, one written by a non-formally educated man, the other a respelling by a formally educated urbanite. The analysis points at a crucial difference in spelling practices and inequality in literacy regimes, i.e., between established orthographic English literacy and the more creative, heterographic and emergent local language literacy. It is shown how English orthography affects local ideologies of literacy as well as Mandinka spelling practices itself, in greater or lesser extent, depending on the educational history of the speller.