Search

Cyberbullying is a serious threat to both the short and long-term well-being of social media users. Addressing this problem in online environments demands the ability to automatically detect cyberbullying and to identify the roles that participants assume in social interactions. As cyberbullying occurs within online communities, it is also vital to understand the group dynamics that support bullying behavior. To this end, we propose a socio-linguistic model which jointly detects cyberbullying content in messages, discovers latent text categories, identifies participant roles and exploits social interactions. While our method makes use of content that is labeled as bullying, it does not require category, role or relationship labels. Furthermore, as bullying labels are often subjective, noisy and inconsistent, an important contribution of our paper is effective methods for leveraging inconsistent labels. Rather than discard inconsistent labels, we evaluate different methods for learning from them, demonstrating that incorporating uncertainty allows for better generalization. Our proposed socio-linguistic model achieves an 18% improvement over state-of-the-art methods.

Based on expert knowledge an adequate logical-linguistic model of the complex system “bio-fermenter-bio fermentation process” was created, which can be used to select the rational operating modes and as a knowledge base when designing an integrated automatic control system of the developed technology.

The aim of this work is to present an ongoing research relating to the use of Twitter by the media; a corpus of 3000 tweets from three TV politic shows are being analized (Los desayunos de TVE, in the public channel TVE1, and Las Mananas Cuatro and Al Rojo Vivo, of private channels Cuatro and La Sexta) and a corpus of 1523 tweets responses produced by followers. The analysis model used is a neuropragmatic based linguistic model, that consider brands of subjectivity and interaction as a direct corollary of the theory of mind.

This paper describes the use of the granular linguistic model of a phenomenon (GLMP) to model the assessment of integer arithmetic learning and implement the automated generation of a formative criterion-based assessment report in natural language, as well as a numerical grade. The report is generated based exclusively on the objective scores automatically generated by Moodle quizzes. GLMP is based on fuzzy logic and the computational theory of perceptions, and uses inference systems based on linguistic rules.

Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images using automatic adaptation to improve accuracy. Our algorithm expects to be given approximate iconic and linguistic models-derived from (generally errorful) OCR results and (generally incomplete) dictionaries-and then, guided entirely by evidence internal to the test set, corrects the models yielding improved accuracy. The iconic model describes image formation and determines the behavior of a character-image classifier. The linguistic model describes word-occurrence probabilities. In previous work, we reported that adapting the iconic model alone (with a perfect linguistic model) was able to automatically reduce word error rate on a 180-page book by a large factor. In this paper, we propose an algorithm that adapts both the iconic model and the linguistic model alternately to improve both models on the fly. The linguistic model adaptation method, which we report here, identifies new words and adds them to the dictionary. With 64.6% words missing in the initial dictionary, our previous algorithm reduced word error rate from 40.2% to 23.2%. The new algorithm drives word error rate down further from 23.2% to 16.0%.

Firstly, this paper constructs a reasonable customer knowledge management(CKM) evaluation indicator system. Secondly, the author constructs the evaluation model of the CKM level based on the directly language two-tuple linguistic and relative operators. This model not only can rank the CKM level of enterprises, but also can achieve the qualitative evaluation. Finally, through demonstrating case, which shows that the evaluation method is simple to use and easy to promote.

A piece of fashionable garment is a piece of art work. In the classical form, a piece of message is hidden or embedded in the art work. The simplified model is in the form of an artist creating the art work which embeds a message to be perceived by the reader. However, to ensure a reader can understand the message correctly, the artist may design the garment and organize the design elements in some systematic way, according to the design theory or semiotics. In this article, a linguistic model is proposed to describe the semiotic structure of the design elements which in turn form a fashion statement. Examples will be demonstrated.