scholarly journals Maximizing the Prediction Accuracy in Tweet Sentiment Extraction using Tensor Flow based Deep Neural Networks

2021 ◽  
Vol 3 (2) ◽  
pp. 61-79
Author(s):  
S Thivaharan ◽  
G Srivatsun
Keyword(s):  
Neural Networks ◽  
Social Media ◽  
Prediction Accuracy ◽  
Deep Neural Networks ◽  
Modern Technology ◽  
The Other ◽  
Data Generation ◽  
Class Prediction ◽  
The Social ◽  
Communication Devices

The amount of data generated by modern communication devices is enormous, reaching petabytes. The rate of data generation is also increasing at an unprecedented rate. Though modern technology supports storage in massive amounts, the industry is reluctant in retaining the data, which includes the following characteristics: redundancy in data, unformatted records with outdated information, data that misleads the prediction and data with no impact on the class prediction. Out of all of this data, social media plays a significant role in data generation. As compared to other data generators, the ratio at which the social media generates the data is comparatively higher. Industry and governments are both worried about the circulation of mischievous or malcontents, as they are extremely susceptible and are used by criminals. So it is high time to develop a model to classify the social media contents as fair and unfair. The developed model should have higher accuracy in predicting the class of contents. In this article, tensor flow based deep neural networks are deployed with a fixed Epoch count of 15, in order to attain 25% more accuracy over the other existing models. Activation methods like “Relu” and “Sigmoid”, which are specific for Tensor flow platforms support to attain the improved prediction accuracy.

Technologies Disability and Inclusion

2018 ◽  
Author(s):  
Tomas Brusell
Keyword(s):  
Social Media ◽  
Augmented Reality ◽  
Information And Communication Technologies ◽  
Future Development ◽  
Smart Cities ◽  
Communication Technologies ◽  
Modern Technology ◽  
The Social ◽  
The Disabled ◽  
Information And Communication

When modern technology permeates every corner of life, there are ignited more and more hopes among the disabled to be compensated for the loss of mobility and participation in normal life, and with Information and Communication Technologies (ICT), Exoskeleton Technologies and truly hands free technologies (HMI), it's possible for the disabled to be included in the social and pedagogic spheres, especially via computers and smartphones with social media apps and digital instruments for Augmented Reality (AR) .In this paper a nouvel HMI technology is presented with relevance for the inclusion of disabled in every day life with specific focus on the future development of "smart cities" and "smart homes".

scholarly journals Loodus tuleb tagasi: delfiinid ja saurused. Libauudistest, photoshop-muistenditest ja meemidest koroonakarantiini ajal

Mäetagused ◽  
2021 ◽  
Vol 79 ◽  
pp. 167-184
Author(s):  
Eda Kalmre ◽  
Keyword(s):  
Social Media ◽  
Coping Strategies ◽  
Well Being ◽  
Point Of View ◽  
Human Existence ◽  
The Other ◽  
Fake News ◽  
The Social ◽  
Truth Value ◽  
Positive Effect

The article follows the narrative trend initiated by the social media posts and fake news during the first months of the corona quarantine, which claims that the decrease of contamination due to the quarantine has a positive effect on the environment and nature recovery. The author describes the context of the topic and follows the changes in the rhetoric through different genres, discussing the ways in which a picture can tell a truthful story. What is the relation between the context, truth, and rhetoric? This material spread globally, yet it was also readily “translated” into the Estonian context, and – what is very characteristic of the entire pandemic material – when approaching this material, truthful and fabricated texts, photos, and videos were combined. From the folkloristic point of view, these rumours in the form of fake news, first presented in the function of a tall tale and further following the sliding truth scale of legends, constitute a part of coping strategies, so-called crisis humour, yet, on the other hand, also a belief story presenting positive imagery, which surrounds the mainly apocalyptically perceived pandemic period and interprets the human existence on a wider scale. Even if these fake news and memes have no truth value, they communicate an idea – nature recovers – and definitely offer hope and a feeling of well-being.

scholarly journals Application of social network analysis for determining the suitable social media influencers

2021 ◽  
Vol 10 (6) ◽  
pp. 348-354
Author(s):  
Mochamad Yudha Febrianta ◽  
Yusditira Yusditira ◽  
Sri Widianesty
Keyword(s):  
Social Media ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Marketing Strategy ◽  
Marketing Strategies ◽  
The Other ◽  
Social Media Marketing ◽  
Other Hand ◽  
The Social

Virtual Hotel Operator (VHO) trend is growing rapidly, especially in Indonesia. Two of the most popular VHO in Indonesia are OYO and RedDoorz, both have been competing to attain the first position. Both OYO and RedDoorz have their own social media marketing strategies. For example, OYO persuades other conventional hotels to collaborate and use the OYO platform in their businesses. On the other hand, RedDoorz was recorded as the most visited Virtual Hotel Operator Platform in 2019, based on the data of Konsumen Jakpat 2019. OYO and RedDoorz also utilize social media to promote their services such as Instagram and Twitter. For advertising their businesses in social media, OYO and RedDoorz often use some social media influencers or known as influencer social media marketing. Influencers should be able to effectively deliver the messages and influence people’s decisions to use the products or services they advertise. This study aims to further explore the social media marketing strategy employed by OYO and RedDoorz. The results of Social Network Analysis by using “oyoindonesia” and ‘reddoorz’ as keywords in social media Twitter showed that RedDoorz has a bigger social network and more users involved in spreading their information than OYO. On the other hand, OYO's official account on Twitter is more efficient in performing its function as marketing media.

Hyperreality of #BlackLivesMatter Movement on Social Media

2021 ◽  
Vol 37 (3) ◽  
pp. 288-303
Author(s):  
Ghozian Aulia Pradhana ◽  
◽  
Syaifa Tania ◽  
Keyword(s):  
Social Media ◽  
African American ◽  
Content Analysis ◽  
Social Networking ◽  
Social Movement ◽  
Social Networking Sites ◽  
The Other ◽  
The Social ◽  
True Meaning ◽  
Social Media Platforms

This study aims to reveal how hyperreality is reflected in using the #BlackLivesMatter hashtag on social media. The death of an African-American, George Floyd, that involved white police, has sparked outrage and demonstrations in many U.S. states. Issues pertaining to racism sparked in relation to the event, and many people protested demanding justice. The demand for justice then went into a wave of massive global protests both in offline and online realities—the #BlackLivesMatter hashtag was widely used on social media when protests were held. The #BlackLivesMatter hashtag even became a trending topic on several social media platforms, as if everyone was concerned about the issue and aiming for the same purpose. However, we might find several posts that neither reflected nor were related to the case. Some social media users put the hashtag even though their content substance was not related. This phenomenon then led to a condition of hyperreality in questioning reality from a simulation of reality. The method used in this study is content analysis which measures the sentiment of comments on Twitter and Instagram. The study found that social networking sites mobilised online movements even though they were not directly related to the #BlackLivesMatter movement. On the other hand, hashtag activism reduced the true meaning of the social movement. Therefore, the hyperreality in #BlackLivesMatter could not be seen any longer as a form of massive protests demanding justice and ending violence, but merely to gain more digital presence on social media. Keywords: Black lives matter, movement, social media, hyperreality, hashtag activism.

The Influence of Modern Media on the Development of Fan Groups and the Promotion of Hooliganism

2016 ◽  
Vol 3 (2) ◽  
pp. 52-62
Author(s):  
Miljana Nikolic
Keyword(s):  
Social Media ◽  
Modern Society ◽  
The Other ◽  
The Internet ◽  
Sport Fans ◽  
Modern Media ◽  
Political Relations ◽  
The Social ◽  
High Level

SummarySince the first sport duels, and with the development of sport through the ages, there were sport fans that cheered either for one or the other opponent and in that way they showed their sympathy. As the time passed, they organized themselves in fan groups, and they became not only an agent of socialization, but also a very important factor in directing social happenings. Hooliganism was created in modern society, and it had devastating effects on both sport and socially-political relations. The functioning of the fan groups that embraces hooliganism, demands high level of organization, so the modern media became a major tool of communication. The aim of this work is to determine in which way, not only the modern media but more importantly the internet sites and the social media of the fan groups, have been used for not only promoting and giving information about their actions, goals and attitude but also promotion of hooliganism.

Shallow and Deep Artificial Neural Networks for Structural Reliability Analysis

2020 ◽  
Author(s):  
Wellison J. S. Gomes
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Reliability Analysis ◽  
Structural Reliability ◽  
Deep Neural Networks ◽  
Surrogate Models ◽  
The Other ◽  
Computational Costs ◽  
Structural Reliability Analysis ◽  
Artificial Neural

Abstract Surrogate models are efficient tools which have been successfully applied in structural reliability analysis, as an attempt to keep the computational costs acceptable. Among the surrogate models available in the literature, Artificial Neural Networks (ANNs) have been attracting research interest for many years. However, the ANNs used in structural reliability analysis are usually the shallow ones, based on an architecture consisting of neurons organized in three layers, the so-called input, hidden and output layers. On the other hand, with the advent of deep learning, ANNs with one input, one output, and several hidden layers, known as deep neural networks, have been increasingly applied in engineering and other areas. Considering that many recent publications have shown advantages of deep over shallow ANNs, the present paper aims at comparing these types of neural networks in the context of structural reliability. By applying shallow and deep ANNs in the solution of four benchmark structural reliability problems from the literature, employing Monte Carlo simulation and adaptive experimental designs, it is shown that, although good results are obtained for both types of ANNs, deep ANNs usually outperform the shallow ones.

scholarly journals MOLI: multi-omics late integration with deep neural networks for drug response prediction

2019 ◽  
Vol 35 (14) ◽  
pp. i501-i509 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Olga Zolotareva ◽  
Colin C Collins ◽  
Martin Ester
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Prediction Accuracy ◽  
Drug Response ◽  
Deep Neural Networks ◽  
Response Prediction ◽  
Supplementary Information ◽  
Precision Oncology

Abstract Motivation Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance. Results We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI’s performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI’s high predictive power suggests it may have utility in precision oncology. Availability and implementation https://github.com/hosseinshn/MOLI. Supplementary information Supplementary data are available at Bioinformatics online.

Assessing flood severity from crowdsourced social media photos with deep neural networks

2020 ◽  
Vol 79 (35-36) ◽  
pp. 26197-26223
Author(s):  
Jorge Pereira ◽  
João Monteiro ◽  
Joel Silva ◽  
Jacinto Estima ◽  
Bruno Martins
Keyword(s):  
Neural Networks ◽  
Social Media ◽  
Deep Neural Networks

Is Social Media Use Socially Enhancing or Compensating?

2020 ◽  
Vol 15 (3) ◽  
pp. 269-288
Author(s):  
Rahul Gadekar ◽  
Peng Hwa Ang
Keyword(s):  
College Students ◽  
Social Media ◽  
Media Use ◽  
The Other ◽  
Social Media Use ◽  
Face To Face ◽  
The Social ◽  
Use Of Social Media ◽  
Manova Analysis ◽  
Compensation Hypothesis

Who benefits more from the use of social media—those who are already socialable and have a wide network of friends or those who do not and so seek to make up for their deficiency by going online? The social enhancement hypothesis says that extroverts benefit more through being able to enlarge their network of friends online more than introverts. The social compensation hypothesis, on the other hand, argues that social media use benefits introverts more; shy users who avoid face-to-face communication can communicate freely online. MANOVA analysis of the survey of 1,392 college students in a western state of India who are Facebook users found evidence predominantly for the social enhancement hypothesis.

Sign in / Sign up

Export Citation Format

Share Document