NEWS CLASSIFICATION WITH HUMAN ANNOTATORS: A CASE STUDY

2015 ◽  
Vol 74 (10) ◽  
Author(s):  
Aini Fuddoly ◽  
Jafreezal Jaafar ◽  
Norshuhani Zamin

The need to classify textual documents has become an increasingly vibrant research field due to the development of online news. While most of the news in news websites are categorised manually, the task becomesmore strenuous considering the tremendous surge of data updates every day. This paper addresses the question of how text classification algorithms can substitute the particular task over manual classification methods. A combined method using Bracewell's algorithm and top-n method is demonstrated and tested using Indonesian language corpus. The experiment also uses human evaluation as the benchmark. The result from the human evaluation is further investigated in order to understand how the annotators classify documents and the aspects that can be improved to enhance the method in the future. The results indicate that the method can outperform human annotators by 13% in terms of accuracy.

2020 ◽  
pp. 016344372097231
Author(s):  
Abdelfettah Benchenna ◽  
Dominique Marchetti

This article presents an overview of the emergence of online news sites, which has radically altered news provision and media consumption patterns in Morocco. This sector has rapidly become a strategic site. Firstly, its precedence over print media and national television networks does not only stem from the high traffic figures of news websites. Along with certain social platforms, these websites are the only vehicules for 24/7 news in a country which currently has just one such news channel and where, in spite of the ‘liberalisation’ of media, national networks provide very institutionalised news programs based on the activities of the state official institutions and of the monarchy. Secondly, certain domestic Arabic-language news websites have become the main platform for the voicing of political dissent. Based on 31 interviews, the article briefly describes the historical development of the online press, since the ‘February 20th Movement’ of 2011. This case study provides a good example of the new challenges surrounding the control of information: an issue long shaped by the limitation of news provision to duly authorised political and journalistic organisations and by limited ‘demand’ resulting from widespread illiteracy. This article describes how the Moroccan establishment react to the explosive growth of online news media by creating new mechanisms to control it.


2021 ◽  
pp. 1-13
Author(s):  
Xiaoyan Wang ◽  
Jianbin Sun ◽  
Qingsong Zhao ◽  
Yaqian You ◽  
Jiang Jiang

It is difficult for many classic classification methods to consider expert experience and classify small-sample datasets well. The evidential reasoning rule (ER rule) classifier can solve these problems. The ER rule has strong processing and comprehensive analysis abilities for diversified mixed information and can solve problems with expert experience effectively. Moreover, the initial parameters of the classifier constructed based on the ER rule can be set according to empirical knowledge instead of being trained by a large number of samples, which can help the classifier classify small-sample datasets well. However, the initial parameters of the ER rule classifier need to be optimized, and choosing the best optimization algorithm is still a challenge. Considering these problems, the ER rule classifier with an optimization operator recommendation is proposed in this paper. First, the initial ER rule classifier is constructed based on training samples and expert experience. Second, the adjustable parameters are optimized, in which the optimization operator recommendation strategy is applied to select the best algorithm by partial samples, and then experiments with full samples are carried out. Finally, a case study on a turbofan engine degradation simulation dataset is carried out, and the results indicate that the ER rule classifier has a higher classification accuracy than other classic classifiers, which demonstrates the capability and effectiveness of the proposed ER rule classifier with an optimization operator recommendation.


2021 ◽  
pp. 174276652110099
Author(s):  
Aleksandra Urman ◽  
Mykola Makhortykh

The paper examines ideological segregation among Ukrainian users in online environments, using as a case study partisan news communities on Vkontakte, the largest online platform in post-communist states. Its findings suggest that despite their insignificant numbers, partisan news communities attract substantial attention from Ukrainian users and can encourage the formation of isolated ideological cliques – or ‘echo chambers’ – that increase societal polarisation. The paper also investigates factors that predict users’ interest in partisan content and establishes that the region of residence is the key predictor of selective consumption of pro-Ukrainian or pro-Russian partisan news content.


2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Nikolas Koch ◽  
Stefan Hartmann ◽  
Antje Endesfelder Quick

AbstractUsage-based approaches assume that children’s early utterances are item-based. This has been demonstrated in a number of studies using the traceback method. In this approach, a small amount of “target utterances” from a child language corpus is “traced back” to earlier utterances. Drawing on a case study of German, this paper provides a critical evaluation of the method from a usage-based perspective. In particular, we check how factors inherent to corpus data as well as methodological choices influence the results of traceback studies. To this end, we present four case studies in which we change thresholds and the composition of the main corpus, use a cross-corpus approach tracing one child’s utterances back to another child’s corpus, and reverse and randomize the target utterances. Overall, the results show that the method can provide interesting insights—particularly regarding different pathways of language acquisition—but they also show the limitations of the method.


Author(s):  
Christof Paulus ◽  
Albert Weber

AbstractVenice is considered the best-informed community of the late Middle Ages. The study examines the availability of information for the second half of the 15th century, particularly with regard to the key year 1462/1463, and as a case study concentrates on areas of the supposed Venetian periphery of interest, above all Hungary and the two principalities of Wallachia and Moldavia. The result is a thoroughly differentiated system of information acquisition, verification and control. Means of communication, as well as different areas of interest of the Serenissima, can be identified. A distinction is made between information maps and communication maps. The latter also include the distribution of news from the lagoon city exchanged with foreign envoys. During the period concerned, news was exchanged in an astonishingly liberal way, in turn integrating the Serenissima into the information networks of the other Italian states. The study thus places the „information commodity“ within the research field of late medieval gift exchange and patronage structures. In short, a thoroughly pragmatic Venetian approach to news acquisition and evaluation can be observed. Verification of the quality of the information obtained was subject not least to quantitative and ranking criteria. Ultimately, the informational power of Venice was based above all on its outstanding reputation among its contemporaries.


2010 ◽  
Vol 11 (2) ◽  
Author(s):  
Amanda Sturgill ◽  
Ryan Pierce ◽  
Yiliu Wang

2011 ◽  
Vol 121-126 ◽  
pp. 1636-1640
Author(s):  
Ying Qiu ◽  
Wei Min Li ◽  
Zhi Wei

Servo presses are widely used in high-precision, complicated forming process fields and promoted around the world in recent years. It is the trend of forging machinery for its servo motor-based digital heavy haul driven technology. At present, it becomes the hot research field. The structure characteristics of triangular elbow servo press were firstly introduced in the paper. And then the kinematics mathematical model of triangular elbow transmission mechanism was deduced and given. Based on it, this paper provides the slider kinematics analysis by Matlab. The slider motion law under various parameters can be analyzed and compared. The results would be useful reference for optimization design of transmission mechanism. The case study provides more visual and reliable decision basis for designer.


Sign in / Sign up

Export Citation Format

Share Document