Political Opinion Analysis in Social Networks: Case of Twitter and Facebook

The 21st century has been characterized by an increased attention to social networks. Nowadays, going 24 hours without getting in touch with them in some way has become difficult. Facebook and Twitter, these social platforms are now part of everyday life. Thus, these social networks have become important sources to be aware of frequently discussed topics or public opinions on a current issue. A lot of people write messages about current events, give their opinion on any topic and discuss social issues more and more. The emergence and enormous popularity of these social networks have led to the emergence of several types of analysis to take advantage of them. One of them is the analysis of opinions in texts. It aims at automatically classifying opinions in order to position them on a sentiment scale, thus allowing to characterize a set of opinions without having to rely on a human to read them. Currently, opinion analysis offers us a lot of information related to public opinion, either in the commercial world or in the political world. Many studies have shown that machine learning techniques, such as the support vector machine (SVM) and the naive Bayes classifier (NB), perform well in this type of classification. In our study, we first propose an approach for tracking and analyzing political opinions in social networks. Then, we propose a trained and evaluated machine learning model for political opinion classification. And finally, the study aims at setting up a web interface to collect and analyze in real time political opinions from social networks

A Self-Supervised Tibetan-Chinese Vocabulary Alignment Method

Tibetan is a low-resource language. In order to alleviate the shortage of parallel corpus between Tibetan and Chinese, this paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-supervised method with seed dictionaries and self-supervised adversarial training method through the similarity calculation of word clusters in different embedded spaces and puts forward an improved selfsupervised adversarial learning method of Tibetan and Chinese monolingual data alignment only. The experimental results are as follows. The seed dictionary of semi-supervised method made before 10 predicted word accuracy of 66.5 (Tibetan - Chinese) and 74.8 (Chinese - Tibetan) results, to improve the self-supervision methods in both language directions have reached 53.5 accuracy.

A Framework for Building a Multilingual Industrial Ontology: Methodology and a Case Study for Building Smartphone English-Arabic Ontology

As Web 3.0 is blooming, ontologies augment semantic Web with semi–structured knowledge. Industrial ontologies can help in improving online commercial communication and marketing. In addition, conceptualizing the enterprise knowledge can improve information retrieval for industrial applications. Having ontologies combine multiple languages can help in delivering the knowledge to a broad sector of Internet users. In addition, multi-lingual ontologies can also help in commercial transactions. This research paper provides a framework model for building industrial multilingual ontologies which include Corpus Determination, Filtering, Analysis, Ontology Building, and Ontology Evaluation. It also addresses factors to be considered when modeling multilingual ontologies. A case study for building a bilingual English-Arabic ontology for smart phones is presented. The ontology was illustrated using an ontology editor and visualization tool. The built ontology consists of 67 classes and 18 instances presented in both Arabic and English. In addition, applications for using the ontology are presented. Future research directions for the built industrial ontology are presented.

Ontology Service Center: A Datahub for Ontology Application

With the growth of data-oriented research in humanities, a large number of research datasets have been created and published through web services. However, how to discover, integrate and reuse these distributed heterogeneous research datasets is a challenging task. Ontology is the soul between series digital humanities resources, which provides a good way for people to discover and understand these datasets. With the release of more and more linked open data and knowledge bases, a large number of ontologies have been produced at the same time. These ontologies have different publishing formats, consumption patterns, and interactions ways, which are not conductive to the user’s understanding of the datasets and the reuse of the ontologies. The Ontology Service Center platform consists of Ontology Query Center and Ontology Validation Center, mainly using linked data and ontology-based technologies. The Ontology Query Center realizes the functions of ontology publishing, querying, data interaction and online browsing, while the Ontology Validation Center can verify the status of using certain ontologies in the linked datasets. The empirical part of the paper uses the Confucius portrait as an example of how OSC can be used in the semantic annotation of images. In a word, the purpose of this paper is to construct the applied ecology of ontology to promote the development of knowledge graphs and the spread of ontology.

Evaluation of Single-Span Models on Extractive Multi-Span Question-Answering

Machine Reading Comprehension (MRC), particularly extractive close-domain question-answering, is a prominent field in Natural Language Processing (NLP). Given a question and a passage or set of passages, a machine must be able to extract the appropriate answer from the passage(s). However, the majority of these existing questions have only one answer, and more substantial testing on questions with multiple answers, or multi-span questions, has not yet been applied. Thus, we introduce a newly compiled dataset consisting of questions with multiple answers that originate from previously existing datasets. In addition, we run BERT-based models pre-trained for question-answering on our constructed dataset to evaluate their reading comprehension abilities. Runtime of base models on the entire dataset is approximately one day while the runtime for all models on a third of the dataset is a little over two days. Among the three of BERT-based models we ran, RoBERTa exhibits the highest consistent performance, regardless of size. We find that all our models perform similarly on this new, multi-span dataset compared to the single-span source datasets. While the models tested on the source datasets were slightly fine-tuned in order to return multiple answers, performance is similar enough to judge that task formulation does not drastically affect question-answering abilities. Our evaluations indicate that these models are indeed capable of adjusting to answer questions that require multiple answers. We hope that our findings will assist future development in question-answering and improve existing question-answering products and methods.

U-mentalism Patent: The Beginning of Cinematic Supercomputation

This paper discloses in synthesis a super-computation computer architecture (CA) model, presently a provisional Patent Application at INPI (nº 116408). The outline is focused on a method to perform computation at or near the speed of light, resorting to an inversion of the Princeton CA. It expands from isomorphic binary/RGB (typical) digital “images”, in a network of (UTM)s over Turing-machines (M)s. From the binary/RGB code, an arithmetic theory of (typical) digital images permits fully synchronous/orthogonal calculus in parallelism, wherefrom an exponential surplus is achieved. One such architecture depends on any “cell”-like exponential-prone basis such as the “pixel”, or rather the RGB “octet-byte”, limited as it may be, once it is congruent with any wave-particle duality principle in observable objects under the electromagnetic spectrum and reprogrammable designed. Well-ordered instructions in binary/RGB modules are, further, programming composed to alter the structure of the Internet, in virtual/virtuous eternal recursion/recurrence, under man-machine/machine-machine communication ontology.