Human Action Prediction Using Sentiment Analysis on Social Networks

2017 ◽  
Vol 6 (2) ◽  
pp. 14-28
Author(s):  
Tatenda Duncan Kavu ◽  
Tinotenda Godknows Nyamandi ◽  
Alleta Chirinda ◽  
Talent T. Rugube ◽  
Kudzai Zishumba
Keyword(s):  
South Africa ◽  
Social Networks ◽  
Probability Theory ◽  
Logistic Regression ◽  
Sentiment Analysis ◽  
Human Action ◽  
Prediction Tool ◽  
Action Prediction ◽  
The Usa ◽  
To Come

There is a rapid increase of mass demonstrations in different locations worldwide triggered by social networks discussions, as witnessed in the USA, Egypt, and South Africa. This paper challenges the underutilization of social media to detect people's' mood and to predict their actions based on their sentiments. Recent published work has demonstrated utility of sentiments on Twitter to predict outcomes of different events, so to come up with the geographical action prediction tool the authors utilized geocodes, sentiment analysis, probability theory, and logistic regression. The tool informs relevant authorities like governments to know the state of people's moods. Entities like business enterprises also benefit from this tool in their plans, especially in avoiding unnecessary costs due to infrastructure destruction.

Using E-Reputation for Sentiment Analysis

2021 ◽  
Vol 11 (2) ◽  
pp. 32-47
Author(s):  
Dhai Eddine Salhi ◽  
Abelkamel Tari ◽  
Mohand Tahar Kechadi
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Logistic Regression ◽  
Sentiment Analysis ◽  
Execution Time ◽  
Supervised Classification ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Mobile Operator ◽  
Strong Point

In a competitive world, companies are looking to gain a positive reputation through these clients. Electronic reputation is part of this reputation mainly in social networks, where everyone is free to express their opinion. Sentiment analysis of the data collected in these networks is very necessary to identify and know the reputation of a companies. This paper focused on one type of data, Twits on Twitter, where the authors analyzed them for the company Djezzy (mobile operator in Algeria), to know their satisfaction. The study is divided into two parts: The first part was the pre-processing phase, where this research filtered the Twits (eliminate useless words, use the tokenization) to keep the necessary information for a better accuracy. The second part was the application of machine learning algorithms (SVM and logistic regression) for a supervised classification since the results are binary. The strong point of this study was the possibility to run the chosen algorithms on a cloud in order to save execution time; the solution also supports the three languages: Arabic, English, and French.

scholarly journals Boundaries of solidarity: a meta-ethnography of mask use during past epidemics to inform SARS-CoV-2 suppression

2021 ◽  
Vol 6 (1) ◽  
pp. e004068
Author(s):  
Po Man Tsang ◽  
Audrey Prost
Keyword(s):  
South Africa ◽  
Risk Perception ◽  
Healthcare Access ◽  
Individual Responsibility ◽  
Trust In Government ◽  
Political Leaders ◽  
Collective Levels ◽  
The Social ◽  
Social Meanings ◽  
The Usa

BackgroundMany countries aiming to suppress SARS-CoV-2 recommend the use of face masks by the general public. The social meanings attached to masks may influence their use, but remain underinvestigated.MethodsWe systematically searched eight databases for studies containing qualitative data on public mask use during past epidemics, and used meta-ethnography to explore their social meanings. We compared key concepts within and across studies, then jointly wrote a critical synthesis.ResultsWe found nine studies from China (n=5), Japan (n=1), Mexico (n=1), South Africa (n=1) and the USA (n=1). All studies describing routine mask use during epidemics were from East Asia. Participants identified masks as symbols of solidarity, civic responsibility and an allegiance to science. This effect was amplified by heightened risk perception (eg, during SARS in 2003), and by seeing masks on political leaders and in outdoor public spaces. Masks also acted as containment devices to manage threats to identity at personal and collective levels. In China and Japan, public and corporate campaigns framed routine mask use as individual responsibility for disease prevention in return for state- or corporate-sponsored healthcare access. In most studies, mask use waned as risk perception fell. In contexts where masks were mostly worn by patients with specific diseases (eg, for patients with tuberculosis in South Africa), or when trust in government was low (eg, during H1N1 in Mexico), participants described masks as stigmatising, uncomfortable or oppressive.ConclusionFace masks can take on positive social meanings linked to solidarity and altruism during epidemics. Unfortunately, these positive meanings can fail to take hold when risk perception falls, rules are seen as complex or unfair, and trust in government is low. At such times, ensuring continued use is likely to require additional efforts to promote locally appropriate positive social meanings, simplifying rules for use and ensuring fair enforcement.

Fuzzy based feature engineering architecture for sentiment analysis of medical discussion over online social networks

2021 ◽  
pp. 1-13
Author(s):  
C S Pavan Kumar ◽  
L D Dhinesh Babu
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Sentiment Analysis ◽  
Membership Function ◽  
Online Social Networks ◽  
Learning Model ◽  
Feature Engineering ◽  
Machine Learning Model ◽  
Social Media Platforms

Sentiment analysis is widely used to retrieve the hidden sentiments in medical discussions over Online Social Networking platforms such as Twitter, Facebook, Instagram. People often tend to convey their feelings concerning their medical problems over social media platforms. Practitioners and health care workers have started to observe these discussions to assess the impact of health-related issues among the people. This helps in providing better care to improve the quality of life. Dementia is a serious disease in western countries like the United States of America and the United Kingdom, and the respective governments are providing facilities to the affected people. There is much chatter over social media platforms concerning the patients’ care, healthy measures to be followed to avoid disease, check early indications. These chatters have to be carefully monitored to help the officials take necessary precautions for the betterment of the affected. A novel Feature engineering architecture that involves feature-split for sentiment analysis of medical chatter over online social networks with the pipeline is proposed that can be used on any Machine Learning model. The proposed model used the fuzzy membership function in refining the outputs. The machine learning model has obtained sentiment score is subjected to fuzzification and defuzzification by using the trapezoid membership function and center of sums method, respectively. Three datasets are considered for comparison of the proposed and the regular model. The proposed approach delivered better results than the normal approach and is proved to be an effective approach for sentiment analysis of medical discussions over online social networks.

Peanut Web Blotch: I. Cultural Characteristics and Identity of Causal Fungus1

1984 ◽  
Vol 11 (2) ◽  
pp. 109-114 ◽  
Author(s):  
R. A. Taber ◽  
R. E. Pettit ◽  
G. L. Philley
Keyword(s):  
South Africa ◽  
Cultural Studies ◽  
Mycelial Growth ◽  
Fungal Species ◽  
Optimum Temperature ◽  
Cultural Characteristics ◽  
Foliar Disease ◽  
The Usa

Abstract A foliar disease of peanuts, previously unreported in the USA, was found in Texas in 1972. The pathogen was identified as a species of Ascochyta. Further cultural studies have revealed this fungus to be Phoma arachidicola Marasas, Pauer, and Boerema. Pycnidia form profusely at 20 C and 25 C. Pycnidiospores are borne on short pycnidiosphores and are predominantly one-celled in culture. Spores produced in pycnidia on infected leaflets become 1 septate. Large 1-septate spores, as well as an occasional 2-septate spore, may form in culture. Optimum temperature for mycelial growth in 20 C; little or no growth occurs at 5 C or above 30 C. The teleomorphic state develops in the field on fallen leaflets and can be induced to form in the laboratory on sterilized peanut leaflets between 15 and 20 C. Cultures derived from single ascospores form pseudothecia. Pycnidiospores, ascospores, and chlamydospores are all infective units. Because this fungus produces hyaline ascospores and pseudoparaphyses, it has been transferred to the genus Didymella as Didymella arachidicola (Choch.) comb. nov. Comparisons with 15 isolates causing web blotch of peanut in the USA, Argentina, and South Africa indicate that web blotch symptoms are produced by the same fungal species.

Psychometric Testing as an Unfair Labour Practice

1986 ◽  
Vol 16 (3) ◽  
pp. 79-86 ◽  
Author(s):  
J.M. Taylor ◽  
E.J. Radford
Keyword(s):  
South Africa ◽  
Ethnic Groups ◽  
Test Scores ◽  
Psychometric Testing ◽  
Moderator Variable ◽  
Ability Test ◽  
Labour Relations ◽  
Ability Tests ◽  
Labour Practice ◽  
The Usa

The concept of unfair labour practice has been introduced into South Africa through the Labour Relations Act and it is argued that certain psychometric testing practices can be interpreted as falling under the definition of an unfair labour practice. Empirical results are presented indicating that different ethnic groups obtain significantly different mean ability test scores. A case-study is cited to show that this would result in underprediction of performance on a criterion for the lower scoring of two groups if test scores are regarded as comparable. It is argued that any interpretation of psychometric data in South Africa that does not take account of possible differences between ethnic groups is likely to ignore a significant moderator variable, given the history of ethnically based discriminatory practices in this country. Arguments based on meta-analytical research in the USA, to the effect that psychometric ability tests do not discriminate unfairly against disadvantaged groups if the same tests and norms are used, should not be assumed to hold in South Africa. Various conceptions of what constitutes fairness in selection are considered, and it is concluded that there is a need for employers to make explicit in their selection policies the trade-off between economic and social costs of employment practices. Finally, some implications for users of psychometric tests in industry are considered, in order to forewarn of likely developments in this field.

scholarly journals Karoo fracking and the Christian faith community

2014 ◽  
Vol 70 (2) ◽  
Author(s):  
Gerrit Van Tonder ◽  
Roger Tucker
Keyword(s):  
South Africa ◽  
Practical Theology ◽  
Oil And Gas ◽  
Environmental Concern ◽  
Faith Community ◽  
Standard Of Living ◽  
Christian Faith ◽  
World Population ◽  
Waste Products ◽  
To Come

One of the challenges for Practical Theology in Africa is to engage with the continent’s concerns and challenges in such a way that the kingdom of God is realised in society and is seen to be relevant to these issues by people who are outside of academia. In our article, which was first presented at the Practical Theology congress in Pretoria in January 2014, the authors seek to demonstrate how this may be accomplished by applying insights to one concern, namely ‘fracking’. The objective is to mobilise the influential Christian faith community in South Africa to begin to exercise prophetic discernment concerning fracking in the Karoo. The fracking debate is a product of the tension between the environmental degradation that its waste products may cause, on the one hand, and, on the other, the greater energy demands of a rapidly increasing world population along with its expectations of an ever-increasing standard of living. Shale gas fracking in the Karoo region of South Africa promises to make vast reserves of oil and gas available to help meet a significant percentage of the country’s energy needs for many years to come, and so thus aid development and contribute to raising the standard of living of many people. Yet the management of the waste products associated with the process is an area of serious environmental concern. The article aims to apprise the South African Christian faith community of the technology and risks involved. Theological guidelines are presented by which fracking’s benefits and dangers can be interrogated so that the community may come to an informed decision as to whether or not to support fracking.

Otta Seals and Gravseals as Low-Cost Surfacing Alternatives for Low-Volume Roads: Experiences in South Africa

2003 ◽  
Vol 1819 (1) ◽  
pp. 338-342 ◽  
Author(s):  
Simon Oloo ◽  
Rob Lindsay ◽  
Sam Mothilal
Keyword(s):  
South Africa ◽  
Low Cost ◽  
Cost Savings ◽  
Cost Effective ◽  
Field Trials ◽  
Low Volume Roads ◽  
Kwazulu Natal ◽  
Traffic Volumes ◽  
Low Volume ◽  
To Come

The geology of the northeastern part of the province of KwaZulu–Natal, South Africa, is predominantly alluvial with vast deposits of sands. Suitable gravel sources are hard to come by, which results in high graveling and regraveling costs brought about by long haul distances and accelerated gravel loss. Most gravel roads carry fewer than 500 vehicles per day of which less than 10% are heavy vehicles. The high cost of regraveling has led to consideration of upgrading such roads to surfaced standard, even though traffic volumes do not justify upgrading. Traditional chip seals are expensive and cannot be economically justified on roads that carry fewer than 500 vehicles per day. The KwaZulu–Natal Department of Transport is actively involved in efforts to identify cost-effective alternative surfacing products for low-volume roads. Field trials were conducted with Otta seals and Gravseals, which have been used successfully in other countries, as low-cost surfacing products for low-volume roads. The Otta seal is formed by placing graded aggregates on a relatively thick film of soft binder that, because of traffic and rolling, works its way through the aggregates. Gravseal consists of a special semipriming rubberized binder that is covered by a graded aggregate. Both Otta seals and Gravseals provide relatively flexible bituminous surfaces suitable for low-volume roads. Cost savings are derived mainly from the broad aggregate specifications, which allow for the use of marginal materials.

Scene-Perception Graph Convolutional Networks for Human Action Prediction

2021 ◽  
Author(s):  
Ji'an Tao ◽  
Lu Xu ◽  
Xinyan Ma ◽  
Jianyu Yan ◽  
Kuizhi Mei
Keyword(s):  
Scene Perception ◽  
Human Action ◽  
Action Prediction ◽  
Convolutional Networks
Sign in / Sign up

Export Citation Format

Share Document