scholarly journals Beyond Raw Performance: Neural Machine Translation Based Multi-lingual Classification of Tweets for Automated Disease Surveillance

2021 ◽  
Author(s):  
Mark Abraham Magumba ◽  
Peter Nabende
Keyword(s):  
Disease Surveillance ◽  
Extraction Methods ◽  
Semantic Context ◽  
Social Phenomena ◽  
Neural Machine Translation ◽  
Disease Occurrence ◽  
The Social ◽  
Standard Information ◽  
Deployed Systems

Abstract Twitter and social media as a whole have great potential as a source of disease surveillance data however the general messiness of tweets presents several challenges for standard information extraction methods. Most deployed systems employ approaches that rely on simple keyword matching and do not distinguish between relevant and irrelevant keyword mentions making them susceptible to false positives as a result of the fact that keyword volume can be influenced by several social phenomena that may be unrelated to disease occurrence. Furthermore, most solutions are intended for a single language and those meant for multilingual scenarios do not incorporate semantic context. In this paper we experimentally examine a translation based approach that allows for incorporation of semantic context in multi-lingual disease surveillance in the social web.

scholarly journals Evaluation of different machine learning approaches and input text representations for multilingual classification of tweets for disease surveillance in the social web

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Mark Abraham Magumba ◽  
Peter Nabende
Keyword(s):  
Disease Surveillance ◽  
Extraction Methods ◽  
Epidemiological Surveillance ◽  
Social Web ◽  
Learning Approaches ◽  
Social Phenomena ◽  
The Social ◽  
Standard Information ◽  
Deployed Systems ◽  
The Impact

AbstractTwitter and social media as a whole have great potential as a source of disease surveillance data however the general messiness of tweets presents several challenges for standard information extraction methods. Most deployed systems employ approaches that rely on simple keyword matching and do not distinguish between relevant and irrelevant keyword mentions making them susceptible to false positives as a result of the fact that keyword volume can be influenced by several social phenomena that may be unrelated to disease occurrence. Furthermore, most solutions are intended for a single language and those meant for multilingual scenarios do not incorporate semantic context. In this paper we experimentally examine different approaches for classifying text for epidemiological surveillance on the social web in addition we offer a systematic comparison of the impact of different input representations on performance. Specifically we compare continuous representations against one-hot encoding for word-based, class-based (ontology-based) and subword units in the form of byte pair encodings. We also go on to establish the desirable performance characteristics for multi-lingual semantic filtering approaches and offer an in-depth discussion of the implications for end-to-end surveillance.

scholarly journals Deep Learning-Based Methods for Sentiment Analysis on Nepali COVID-19-Related Tweets

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
C. Sitaula ◽  
A. Basnet ◽  
A. Mainali ◽  
T. B. Shahi
Keyword(s):  
Feature Extraction ◽  
Sentiment Analysis ◽  
Extraction Methods ◽  
The Novel ◽  
Domain Specific ◽  
The Social ◽  
Stable Performance ◽  
Media Platform ◽  
The Web

COVID-19 has claimed several human lives to this date. People are dying not only because of physical infection of the virus but also because of mental illness, which is linked to people’s sentiments and psychologies. People’s written texts/posts scattered on the web could help understand their psychology and the state they are in during this pandemic. In this paper, we analyze people’s sentiment based on the classification of tweets collected from the social media platform, Twitter, in Nepal. For this, we, first, propose to use three different feature extraction methods—fastText-based (ft), domain-specific (ds), and domain-agnostic (da)—for the representation of tweets. Among these three methods, two methods (“ds” and “da”) are the novel methods used in this study. Second, we propose three different convolution neural networks (CNNs) to implement the proposed features. Last, we ensemble such three CNNs models using ensemble CNN, which works in an end-to-end manner, to achieve the end results. For the evaluation of the proposed feature extraction methods and CNN models, we prepare a Nepali Twitter sentiment dataset, called NepCOV19Tweets, with 3 classes (positive, neutral, and negative). The experimental results on such dataset show that our proposed feature extraction methods possess the discriminating characteristics for the sentiment classification. Moreover, the proposed CNN models impart robust and stable performance on the proposed features. Also, our dataset can be used as a benchmark to study the COVID-19-related sentiment analysis in the Nepali language.

scholarly journals Design Choices for Automated Disease Surveillance in the Social Web

2018 ◽  
Vol 10 (2) ◽  
Author(s):  
Mark Abraham Magumba ◽  
Peter Nabende ◽  
Ernest Mwebaze
Keyword(s):  
Disease Surveillance ◽  
Information Dissemination ◽  
Experimental Studies ◽  
User Participation ◽  
Social Web ◽  
Functional Aspects ◽  
The Social ◽  
Surveillance Programs ◽  
High Level ◽  
Deployed Systems

The social web has emerged as a dominant information architecture accelerating technology innovation on an unprecedented scale. The utility of these developments to public health use cases like disease surveillance, information dissemination, outbreak prediction and so forth has been widely investigated and variously demonstrated in work spanning several published experimental studies and deployed systems. In this paper we provide an overview of automated disease surveillance efforts based on the social web characterized by their different high level design choices regarding functional aspects like user participation and language parsing approaches. We briefly discuss the technical rationale and practical implications of these different choices in addition to the key limitations associated with these systems within the context of operable disease surveillance. We hope this can offer some technical guidance to multi-disciplinary teams on how best to implement, interpret and evaluate disease surveillance programs based on the social web.

scholarly journals Is shooting a sport? The outline of sport shooting in Poland as a subject matter of the sociology of sport

2020 ◽  
pp. 33-48
Author(s):  
Piotr Adam Zwarycz
Keyword(s):  
Subject Matter ◽  
Social World ◽  
Social Phenomena ◽  
Sociology Of Sport ◽  
The Social ◽  
Methodological Considerations

The main goals of this text are to answer the question of whether sport shooting should be treated as a sport and to convince readers that shooting can be an interesting subject within the sociology of sport. Sport shooting is an activity that is dynamically developing and has engaged more and more people in recent years in Poland. The article presents the history and specificity of this sport discipline, including the presentation of the competition and the classification of people participating in the social world of shooters. The text also contains preliminary conclusions on social phenomena concerning the shooting environment and methodological considerations related to barriers occurring in the study of this environment.

Social-Psychological Models in Labor Motivation Analysis

2004 ◽  
pp. 90-101 ◽  
Author(s):  
A. Surkov
Keyword(s):  
Economic Analysis ◽  
Psychological Approach ◽  
Social Psychological ◽  
Economic Man ◽  
The Social ◽  
Psychological Models ◽  
Social Psychological Approach

Benefits of using social-psychological approach in the analysis of labor motivations are considered in the article. Classification of employees as objects of economic analysis is offered: "the economic man", "the man of the organization", "the social man" and "the asocial man". Related models give the opportunity to predict behavior of the firm in different situations, such as shocks of various nature.

“We Speak the Truth!”

2019 ◽  
Vol 12 (2) ◽  
pp. 53-80
Author(s):  
Sari Hanafi
Keyword(s):  
Social Sciences ◽  
Content Analysis ◽  
Social Science ◽  
The Political ◽  
Structured Interviews ◽  
Social Phenomena ◽  
The Social ◽  
Academic Qualifications

This study investigates the preachers and their Friday sermons in Lebanon, raising the following questions: What are the profiles of preachers in Lebanon and their academic qualifications? What are the topics evoked in their sermons? In instances where they diagnosis and analyze the political and the social, what kind of arguments are used to persuade their audiences? What kind of contact do they have with the social sciences? It draws on forty-two semi-structured interviews with preachers and content analysis of 210 preachers’ Friday sermons, all conducted between 2012 and 2015 among Sunni and Shia mosques. Drawing from Max Weber’s typology, the analysis of Friday sermons shows that most of the preachers represent both the saint and the traditional, but rarely the scholar. While they are dealing extensively with political and social phenomena, rarely do they have knowledge of social science

Kaki Manusia Sebagai Objek Estetik Penciptaan Fotografi Seni

2014 ◽  
Author(s):  
Dira Herawati
Keyword(s):  
Social Situation ◽  
Work Of Art ◽  
Social Phenomena ◽  
Aesthetic Object ◽  
Human Foot ◽  
Works Of Art ◽  
The Social ◽  
The Creation ◽  
Art Photography ◽  
Artistic Images

Accountability report is a written description of creative experiences as an artist or a photographer of aesthetic exploration efforts on the image and the idea of a human as a basic stimulant for the creation of works of art photography. Human foot as an aesthetic object is a problem that relates to various phenomena that occur in the social sphere, culture and politics in Indonesia today. Based on these linkages, human feet would be formulated as an image that has a value, and the impression of eating alone in the creation of a work of art photography. Hence the creation of this art photography entitled The Human Foots as Aesthetic Object  Creation of Art Photography. Starting from this background, then the legs as an option object art photography, will be managed creatively and systematically through a phases of creation. The creation phases consist of: (1) the exploration of discourse, (2) artistic exploration, (3) the stage of elaboration photographic, (4) the synthesis phase, and (5) the stage of completion. Methodically, through the phases of the creative process  through which this can then be formulated in various forms of artistic image of a human foot. The various forms of artistic images generated from the foots of its creation process, can be summed up as an object of aesthetic order 160 Kaki Manusia Sebagai Objek Estetik Penciptaan Fotografi Seni in the photographic works of art. It is specifically characterized by the formation of ‘imaging the other’ behind the image seen with legs visible, as well as of the various forms of ‘new image’ as a result of an artistic exploration of the common image of legs visible. In general, the whole image of the foot in a photographic work of art has a reflective relationship with the social situation, cultures, and politics that developed in Indonesian society, by value, meaning and impression that it contains.Keywords: human foots, aestheti,; social phenomena, art photography, images

Philosophcal review of h. white̕s tropological theory in the context of the new philosophy of history

2020 ◽  
Vol 3 (152) ◽  
pp. 92-99
Author(s):  
S. M. Geiko ◽  
◽  
O. D. Lauta
Keyword(s):  
Modern Science ◽  
Historical Knowledge ◽  
Text Organization ◽  
The Social ◽  
History Of ◽  
Actual Material ◽  
The Common ◽  
Historical Nature ◽  
Selection Of

The article provides a philosophical analysis of the tropological theory of the history of H. White. The researcher claims that history is a specific kind of literature, and the historical works is the connection of a certain set of research and narrative operations. The first type of operation answers the question of why the event happened this way and not the other. The second operation is the social description, the narrative of events, the intellectual act of organizing the actual material. According to H. White, this is where the set of ideas and preferences of the researcher begin to work, mainly of a literary and historical nature. Explanations are the main mechanism that becomes the common thread of the narrative. The are implemented through using plot (romantic, satire, comic and tragic) and trope systems – the main stylistic forms of text organization (metaphor, metonymy, synecdoche, irony). The latter decisively influenced for result of the work historians. Historiographical style follows the tropological model, the selection of which is determined by the historian’s individual language practice. When the choice is made, the imagination is ready to create a narrative. Therefore, the historical understanding, according to H. White, can only be tropological. H. White proposes a new methodology for historical research. During the discourse, adequate speech is created to analyze historical phenomena, which the philosopher defines as prefigurative tropological movement. This is how history is revealed through the art of anthropology. Thus, H. White’s tropical history theory offers modern science f meaningful and metatheoretically significant. The structure of concepts on which the classification of historiographical styles can be based and the predictive function of philosophy regarding historical knowledge can be refined.

The Tinder Games: Collective mobile dating app use and gender conforming behavior

2021 ◽  
pp. 205015792110050
Author(s):  
Sabrina Sobieraj ◽  
Lee Humphreys
Keyword(s):  
Young Adults ◽  
Focus Group ◽  
Research Approach ◽  
Social Phenomena ◽  
Social Nature ◽  
Dating Apps ◽  
The Social ◽  
And Gender ◽  
Multi Phase ◽  
Gender Specific

Mobile dating apps like Tinder became very popular among young adults, and, in contrast to mobile dating websites, they were designed to create a more game-like experience. While it is well documented that seeking entertainment is one core motivation for mobile dating app use, the social nature of entertainment has garnered less attention. Therefore, in this paper we draw on research on entertainment in dating apps and the socio-physical contexts of use to identify patterned behaviors of heterosexual users. To do this, we employed a qualitative multi-phase research approach. First, we conducted 20 interviews with mobile dating app users. Based on the findings from that study, we conducted gender-specific focus groups and a discourse analysis to explore the social phenomena identified in phase one. Our findings suggest the fun of mobile dating is not just interacting with potential matches through the apps, but the use of the apps among one’s friends. These “dating games” are entertaining, but importantly mitigate potential social or physical risks of mobile dating. Unsurprisingly, notions of “play” across the interview, focus group, and discourse analyses reflect highly gendered practices surrounding mobile dating apps and different risks associated with such games.

Sign in / Sign up

Export Citation Format

Share Document