scholarly journals Evolution of topics and hate speech in retweet network communities

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Bojan Evkoski ◽  
Nikola Ljubešić ◽  
Andraž Pelicon ◽  
Igor Mozetič ◽  
Petra Kralj Novak
Keyword(s):  
Hate Speech ◽  
Temporal Evolution ◽  
Three Dimensions ◽  
Temporal Dimension ◽  
Community Membership ◽  
Twitter Data ◽  
Network Communities ◽  
Topic Distribution ◽  
Textual Content

AbstractTwitter data exhibits several dimensions worth exploring: a network dimension in the form of links between the users, textual content of the tweets posted, and a temporal dimension as the time-stamped sequence of tweets and their retweets. In the paper, we combine analyses along all three dimensions: temporal evolution of retweet networks and communities, contents in terms of hate speech, and discussion topics. We apply the methods to a comprehensive set of all Slovenian tweets collected in the years 2018–2020. We find that politics and ideology are the prevailing topics despite the emergence of the Covid-19 pandemic. These two topics also attract the highest proportion of unacceptable tweets. Through time, the membership of retweet communities changes, but their topic distribution remains remarkably stable. Some retweet communities are strongly linked by external retweet influence and form super-communities. The super-community membership closely corresponds to the topic distribution: communities from the same super-community are very similar by the topic distribution, and communities from different super-communities are quite different in terms of discussion topics. However, we also find that even communities from the same super-community differ considerably in the proportion of unacceptable tweets they post.

scholarly journals Glimpse: A Gaze-Based Measure of Temporal Salience

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3099
Author(s):  
V. Javier Traver ◽  
Judith Zorío ◽  
Luis A. Leiva
Keyword(s):  
Visual Attention ◽  
Computational Models ◽  
Temporal Evolution ◽  
Temporal Consistency ◽  
Visual Salience ◽  
Temporal Dimension ◽  
Spatial Perspective ◽  
Spatio Temporal ◽  
Scoring Algorithms ◽  
Over Time

Temporal salience considers how visual attention varies over time. Although visual salience has been widely studied from a spatial perspective, its temporal dimension has been mostly ignored, despite arguably being of utmost importance to understand the temporal evolution of attention on dynamic contents. To address this gap, we proposed Glimpse, a novel measure to compute temporal salience based on the observer-spatio-temporal consistency of raw gaze data. The measure is conceptually simple, training free, and provides a semantically meaningful quantification of visual attention over time. As an extension, we explored scoring algorithms to estimate temporal salience from spatial salience maps predicted with existing computational models. However, these approaches generally fall short when compared with our proposed gaze-based measure. Glimpse could serve as the basis for several downstream tasks such as segmentation or summarization of videos. Glimpse’s software and data are publicly available.

scholarly journals Herramientas e indicadores para el análisis de la temporalidad en el periodismo digital y el documental interactivo

2020 ◽  
pp. 25-37
Author(s):  
Pere Freixa
Keyword(s):  
Large Scale ◽  
Temporal Evolution ◽  
Close Reading ◽  
Redes Sociales ◽  
Temporal Dimension ◽  
The Public ◽  
Active Reading ◽  
Digital Ecosystem ◽  
Digital Journalism ◽  
Methodological Reflection

Over the last two decades, digital journalism and interactive documentaries have produced works in which interactivity, multimedia, and participation articulate the access and consumption of information. These are basically multimedia and dynamic texts that delve into two-way communication and hypertext, and motivate active reading. These are informational pieces typical of the digital ecosystem that often mutate via social networks and present significant transformations in their temporal evolution. Reading, analyzing, and understanding these texts requires specific tools and methodologies that consider: (a) the dynamism of such pieces, as well as their temporal modification, (b) their multimodal dimension, and (c) their transmedia development. This article proposes a methodological reflection on the ways of reading interactive documentary audiovisual texts and proposes strategies and tools for their understanding and analysis based on detailed reading (close reading), and decoupage. This research focuses on an analysis of the temporal evolution of these journalistic pieces. The need to observe and analyze the temporal dimension of journalistic texts in the digital ecosystem has allowed the development of specific methodologies (Widholm, 2016; Karlsson; Sjøvaag, 2016; Buhl; Günther; Quandt, 2018) focused on the immediacy and mutability of journalistic news, its permanence in networks, and its temporal evolution. However, these tools do not consider the study of large-scale journalistic stories, typical of interactive documentaries, which require a specific multimodal approach (Hiippala, 2017; Van-Krieken, 2018, Freixa et al., 2014; Freixa, 2015). A detailed reading reveals how the interactive documentary considers the dimension, both temporal and of content and form, of the traditional documentary text, by becoming part of a transmedia framework as part of a dialogue with the public. Resumen Desde hace dos décadas, el periodismo digital y el documental interactivo produce obras en las que la interactividad, la multimedialidad y la participación articulan el acceso y consumo de la información. Básicamente se trata de textos multimediales y dinámicos, que ahondan en la comunicación bidireccional y el hipertexto, y que proponen lecturas activas. Se trata de piezas informacionales propias del ecosistema digital que, a menudo, mutan en las redes sociales y presentan significativas transformaciones en su evolución temporal. La lectura, el análisis y la comprensión de estos textos precisa de herramientas y metodologías específicas que contemplen: a) el dinamismo de las piezas, así como su modificación temporal; b) su dimensión multimodal y c) su desarrollo transmedia. En este artículo se propone una reflexión metodológica sobre las formas de lectura de los textos audiovisuales interactivos documentales, y se proponen estrategias y herramientas para su comprensión y análisis basadas en la lectura detallada (close reading), y el découpage. La investigación focaliza su interés en el análisis de la evolución temporal de estas piezas periodísticas. La necesidad de observar y analizar la dimensión temporal de los textos periodísticos en el ecosistema digital ha permitido el desarrollo de metodologías específicas (Widholm, 2016; Karlsson; Sjøvaag, 2016; Buhl; Günther; Quandt, 2018) focalizadas en la inmediatez y mutabilidad de la noticia periodística, su permanencia en red y evolución temporal. Estas herramientas, sin embargo, no contemplan el estudio de los relatos periodísticos de gran dimensión, propios del documental interactivo, que precisan de una aproximación multimodal específica (Hiippala, 2017; Van-Krieken, 2018, Freixa et al., 2014; Freixa, 2015). La lectura detallada permite observar cómo el documental interactivo cuestiona la dimensión, tanto temporal como de contenido y forma, del texto documental tradicional, al pasar a formar parte de un entramado transmedia en diálogo con el público.

Narrowing the Gap between China and Japan: Three Dimensions of National Identity and the Korean Factor

2013 ◽  
Vol 14 (1) ◽  
pp. 31-49
Author(s):  
GILBERT ROZMAN
Keyword(s):  
National Identity ◽  
Shared Vision ◽  
Three Dimensions ◽  
Test Case ◽  
Temporal Dimension ◽  
Bilateral Relations ◽  
The Us ◽  
East Asian Community ◽  
Yasukuni Shrine ◽  
Political Economic

AbstractIn 2010–12, Sino-Japanese relations deteriorated without the Yasukuni Shrine or Chinese human rights violations in the forefront. To improve relations, attention should turn to what I label the ideological, sectoral, and horizontal dimensions of a national identity gap between these countries. They have each figured in the decline and offer more promise than the temporal dimension, with its symbols of wartime memories, and the vertical dimension, where sensitive Chinese internal affairs are at stake. The sectoral dimension comprises political, economic, and also cultural national identity, each of which has grown more intense in China, while cultural identity is still a force in Japan. Establishing an East Asian community is now the centerpiece in the hope that the horizontal dimension will be an impetus for mutual understanding, yet the notion of community is repeated with no sign of a shared vision of the outside world, whether the US role or the international arena and regionalism. With South Korea, their partner in trilateralism and North Korea's transformation at the crux of all three of these dimensions, this paper emphasizes the way divergent views of the peninsula keep growing in importance for bilateral relations. It suggests ways to reframe relations through cooperation over Korea. As difficult as Korean relations are for both states, it is a test case for their identity gap.

scholarly journals Occurrence Cubes: A new way of aggregating heterogeneous species occurrence data

2020 ◽  
Vol 4 ◽  
Author(s):  
Damiano Oldoni ◽  
Quentin Groom ◽  
Peter Desmet
Keyword(s):  
Dimensional Space ◽  
Species Level ◽  
Three Dimensions ◽  
Spatial Uncertainty ◽  
Species Occurrence ◽  
Temporal Dimension ◽  
Area Of Occupancy ◽  
Occurrence Data ◽  
Research Infrastructures ◽  
Reference Grid

The digital era has brought about an impressive increase in the volume of published species occurrence data. Research infrastructures such as the Global Biodiversity Information Facility (GBIF), the digitization of legacy data, and the use of mobile applications have all played a role in this transition. More data implies, unavoidably, more heterogeneity at multiple levels as a result of the different methods and standards used to collect data. Data standardization and aggregation help to reduce this heterogeneity. Furthermore, intermediate data products that can be used for activities such as mapping, modeling and monitoring improve the repeatability and reproducibility of biodiversity research (Kissling et al. 2017). Occurrences can be defined as events in a three-dimensional space where the dimensions are taxonomic (what), temporal (when) and spatial (where). They are then aggregated into what we coined occurrence cube (Fig. 1). The taxonomic dimension is categorical. Research infrastructures like GBIF use a taxonomic backbone, thus making data aggregation at species level or higher rank relatively easy. The temporal dimension is a continuum and the temporal uncertainty is usually lower than the typical aggregation span, typically a year. Regarding the spatial dimension, occurrences are typically filtered to remove those with too large an uncertainty to fit the grid scheme being used. Meaning that the spatial uncertainty is largely unused. We developed a method to take into account this spatial uncertainty while aggregating data. In particular, we state that an occurrence is spatially representable as a closed plane figure such as a circle, hexagon or square, never as the geometric centre (centroid) of it. As for GBIF occurrence data, the coordinateUncertaintyInMeters is defined as the radius describing the smallest circle containing the whole of the location (see Darwin Core standard). So, spatially speaking, we refer to occurrences as circles, even if the method described below is general. After harvesting the occurrence data and providing a data quality assessment (e.g. removing occurrences without coordinates or with suspicious coordinates) we can assign occurrences to a reference grid such as the European reference grid of the European Environment Agency (EEA) at 1 km scale. In this spatial aggregation we randomly choose a point within the occurrence circle and assign it to the grid cell in which it is contained. We can aggregate further by time (e.g. by year) and taxonomy (e.g. by species), where aggregating means counting how many occurrences are in each specific taxonomic-spatial-temporal unit. The analogy with geometry goes further: the occurrence cube can, as any cube, be projected on an orthogonal plane by aggregating along one of the three dimensions. In particular, projecting the cube on the taxonomic and temporal dimensions can be done by adding up the number of occurrences, or counting the number of occupied cells, thus estimating the area of occupancy. The occurrence cube paradigm has been developed within the Tracking Invasive Alien Species (TrIAS) project (Vanderhoeven et al. 2017) following Open Science and FAIR principles. We created and published occurrence cubes at the species level for Belgium and Italy (Oldoni et al. 2020b) and the occurrence cubes for non-native taxa in Belgium and Europe (Oldoni et al. 2020a).

Transition in spacetime

2014 ◽  
Vol 6 (2) ◽  
pp. 1202-1210
Author(s):  
Mostafa Mohamed Korany
Keyword(s):  
Spatial Dimension ◽  
The Other ◽  
Three Dimensions ◽  
Theory Of Relativity ◽  
Spacetime Dimension ◽  
Time And Space ◽  
Temporal Dimension ◽  
The Universe ◽  
Dimensions Of Space

The universe has two main dimensions spatial dimension (consists of three dimensions directional X, Y, Z) and the other dimension is the temporal dimension. Time and space are linked strongly inseparable so we will consider the time and place one Is the dimension of spacetime (as proved Einstein in his theory of relativity). Spacetime dimension includes the temporal dimension and spatial dimension (the three dimensions of space).  Spacetime dimension two (real spacetime – Vision spacetime).  Spacetime has two cases:    1- Navigate spacetime       2- The change in spacetime. spacetime is Personally like a fingerprint and it always variable ( everyone has Personally spacetime and there are not find two of spacetime are the same.

scholarly journals MaLang: A Decentralized Deep Learning Approach for Detecting Abusive Textual Content

2021 ◽  
Vol 11 (18) ◽  
pp. 8701
Author(s):  
Pranav Kompally ◽  
Sibi Chakkaravarthy Sethuraman ◽  
Steven Walczak ◽  
Samuel Johnson ◽  
Meenalosini Vimal Cruz
Keyword(s):  
Deep Learning ◽  
Hate Speech ◽  
System Level ◽  
Learning Approach ◽  
Unique Identifier ◽  
Detection Systems ◽  
Learning Techniques ◽  
Cyberbullying Detection ◽  
Textual Content ◽  
Deep Learning Model

Cyberbullying is a growing and significant problem in today’s workplace. Existing automated cyberbullying detection solutions rely on machine learning and deep learning techniques. It is proven that the deep learning-based approaches produce better accuracy for text-based classification than other existing approaches. A novel decentralized deep learning approach called MaLang is developed to detect abusive textual content. MaLang is deployed at two levels in a network: (1) the System Level and (2) the Cloud Level, to tackle the usage of toxic or abusive content on any messaging application within a company’s networks. The system-level module consists of a simple deep learning model called CASE that reads the user’s messaging data and classifies them into abusive and non-abusive categories, without sending any raw or readable data to the cloud. Identified abusive messages are sent to the cloud module with a unique identifier to keep user profiles hidden. The cloud module, called KIPP, utilizes deep learning to determine the probability of a message containing different categories of toxic content, such as: ‘Toxic’, ‘Insult’, ‘Threat’, or ‘Hate Speech’. MaLang achieves a 98.2% classification accuracy that outperforms other current cyberbullying detection systems.

scholarly journals Effective hate-speech detection in Twitter data using recurrent neural networks

2018 ◽  
Vol 48 (12) ◽  
pp. 4730-4742 ◽  
Author(s):  
Georgios K. Pitsilis ◽  
Heri Ramampiaro ◽  
Helge Langseth
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Hate Speech ◽  
Speech Detection ◽  
Twitter Data
Sign in / Sign up

Export Citation Format

Share Document