scholarly journals BlueMemo: Depression Analysis through Twitter Posts

2020 ◽  
Author(s):  
Pengwei Hu ◽  
Chenhao Lin ◽  
Hui Su ◽  
Shaochun Li ◽  
Xue Han ◽  
...  
Keyword(s):  
Social Media ◽  
Potential Risk ◽  
Image Features ◽  
Classification Model ◽  
Hidden Information ◽  
Visual Attributes ◽  
Depressed Patients ◽  
Text Features ◽  
Use Of Social Media ◽  
New System

The use of social media runs through our lives, and users' emotions are also affected by it. Previous studies have reported social organizations and psychologists using social media to find depressed patients. However, due to the variety of content published by users, it isn't effortless for the system to consider the text, image, and even the hidden information behind the image. To address this problem, we proposed a new system for social media screening of depressed patients named BlueMemo. We collected real-time posts from Twitter. Based on the posts, learned text features, image features, and visual attributes were extracted as three modalities and were fed into a multi-modal fusion and classification model to implement our system. The proposed BlueMemo has the power to help physicians and clinicians quickly and accurately identify users at potential risk for depression.

scholarly journals Predicting Implicit User Preferences with Multimodal Feature Fusion for Similar User Recommendation in Social Media

2021 ◽  
Vol 11 (3) ◽  
pp. 1064
Author(s):  
Jenq-Haur Wang ◽  
Yen-Tsang Wu ◽  
Long Wang
Keyword(s):  
Social Media ◽  
Feature Fusion ◽  
Relevant Information ◽  
Image Features ◽  
User Preferences ◽  
User Preference ◽  
Late Fusion ◽  
Multimodal Features ◽  
Fusion Methods ◽  
Text Features

In social networks, users can easily share information and express their opinions. Given the huge amount of data posted by many users, it is difficult to search for relevant information. In addition to individual posts, it would be useful if we can recommend groups of people with similar interests. Past studies on user preference learning focused on single-modal features such as review contents or demographic information of users. However, such information is usually not easy to obtain in most social media without explicit user feedback. In this paper, we propose a multimodal feature fusion approach to implicit user preference prediction which combines text and image features from user posts for recommending similar users in social media. First, we use the convolutional neural network (CNN) and TextCNN models to extract image and text features, respectively. Then, these features are combined using early and late fusion methods as a representation of user preferences. Lastly, a list of users with the most similar preferences are recommended. The experimental results on real-world Instagram data show that the best performance can be achieved when we apply late fusion of individual classification results for images and texts, with the best average top-k accuracy of 0.491. This validates the effectiveness of utilizing deep learning methods for fusing multimodal features to represent social user preferences. Further investigation is needed to verify the performance in different types of social media.

scholarly journals Using Machine Learning to Detect Events on the Basis of Bengali and Banglish Facebook Posts

Electronics ◽  
2021 ◽  
Vol 10 (19) ◽  
pp. 2367
Author(s):  
Noyon Dey ◽  
Md. Sazzadur Rahman ◽  
Motahara Sabah Mredula ◽  
A. S. M. Sanwar Hosen ◽  
In-Ho Ra
Keyword(s):  
Social Media ◽  
Detection System ◽  
Classification Model ◽  
Support Vector ◽  
Proposed Model ◽  
Prime Concern ◽  
Use Of Social Media ◽  
Bengali Language ◽  
Language Detection ◽  
Media Data

In modern times, ensuring social security has become the prime concern for security administrators. The widespread and recurrent use of social media sites is creating a huge risk for the lives of the general people, as these sites are frequently becoming potential sources of the organization of various types of immoral events. For protecting society from these dangers, a prior detection system which can effectively detect events by analyzing these social media data is essential. However, automating the process of event detection has been difficult, as existing processes must account for diverse writing styles, languages, dialects, post lengths, and et cetera. To overcome these difficulties, we developed an effective model for detecting events, which, for our purposes, were classified as either protesting, celebrating, religious, or neutral, using Bengali and Banglish Facebook posts. At first, the collected posts’ text were processed for language detection, and then, detected posts were pre-processed using stopwords removal and tokenization. Features were then extracted from these pre-processed texts using three sub-processes: filtering, phrase matching of specific events, and sentiment analysis. The collected features were ultimately used to train our Bernoulli Naive Bayes classification model, which was capable of detecting events with 90.41% accuracy (for Bengali-language posts) and 70% (for the Banglish-form posts). For evaluating the effectiveness of our proposed model more precisely, we compared it with two other classifiers: Support Vector Machine and Decision Tree.

scholarly journals Buzz Tweet Classification Based on Text and Image Features of Tweets Using Multi-Task Learning

2021 ◽  
Vol 11 (22) ◽  
pp. 10567
Author(s):  
Reishi Amitani ◽  
Kazuyuki Matsumoto ◽  
Minoru Yoshida ◽  
Kenji Kita
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Detailed Analysis ◽  
Image Features ◽  
Analysis Method ◽  
Text And Image ◽  
Multiple Features ◽  
Single Feature ◽  
Text Features ◽  
Tweet Classification

This study investigates social media trends and proposes a buzz tweet classification method to explore the factors causing the buzz phenomenon on Twitter. It is difficult to identify the causes of the buzz phenomenon based solely on texts posted on Twitter. It is expected that by limiting the tweets to those with attached images and using the characteristics of the images and the relationships between the text and images, a more detailed analysis than that of with text-only tweets can be conducted. Therefore, an analysis method was devised based on a multi-task neural network that uses both the features extracted from the image and text as input and the buzz class (buzz/non-buzz) and the number of “likes (favorites)” and “retweets (RTs)” as output. The predictions made using a single feature of the text and image were compared with the predictions using a combination of multiple features. The differences between buzz and non-buzz features were analyzed based on the cosine similarity between the text and the image. The buzz class was correctly identified with a correctness rate of approximately 80% for all combinations of image and text features, with the combination of BERT and VGG16 providing the highest correctness rate.

scholarly journals Education in the Disruption Era

2019 ◽  
Vol 1 (2) ◽  
pp. 183-188
Author(s):  
Fitriani Lubis
Keyword(s):  
Social Media ◽  
Online Tutoring ◽  
Conventional Teaching ◽  
The World ◽  
Use Of Social Media ◽  
The Times ◽  
New System

The disruption era is the occurrence of fundamental changes in all aspects of life. The new system comes to replace the old and obsolete system that is not in accordance with the requirements of the times. In terms of education, disruption will change conventional teaching patterns to digital. The emergence of innovative applications in the world of education can make it easier for everyone to seek knowledge wherever and whenever. The use of social media or online tutoring applications now is greatly benefits for the reach of a wider and more equal audience. This study will discuss the need for our understanding of education in the era of disruption, and how educators deal with this phenomenon with more emphasis on the need for education that can better adapt to current conditions.

Web-Based Financial Reporting: An Interpretative Model for Corporate Communications on Social Media

2017 ◽  
pp. 79-112
Author(s):  
Paola Ramassa ◽  
Costanza Di Fabio
Keyword(s):  
Social Media ◽  
Financial Reporting ◽  
Building Blocks ◽  
Corporate Communications ◽  
Distinctive Features ◽  
Financial Communication ◽  
Use Of Social Media ◽  
Key Aspects ◽  
And Diffusion ◽  
Interpretative Model

This paper aims at contributing to financial reporting literature by proposing a conceptual interpretative model to analyse the corporate use of social media for financial communication purposes. In this perspective, the FIRE model provides a framework to study social media shifting the focus on the distinctive features that might enhance web investor relations. The model highlights these features through four building blocks: (i) firm identity (F); (ii) information posting (I); (iii) reputation (R); and (iv) exchange and diffusion (E). They represent key aspects to explore corporate communication activities and might offer a framework to interpret to what degree corporate web financial reporting exploits the potential of social media. Accordingly, the paper proposes metrics based on this model aimed at capturing the interactivity of corporate communications via social media, with a particular focus on web financial reporting. It tries to show the potential of this model by illustrating an exploratory empirical analysis investigating to what extent companies use social media for financial reporting purposes and whether firms are taking advantage of Twitter distinctive features of interaction and diffusion.

Maqâṣid Al-Qur’ân In The Interpretation of M. Quraish Shihab About The Verse of Social Media Usage

2020 ◽  
Vol 28 (1) ◽  
pp. 44
Author(s):  
Johar Arifin ◽  
Ilyas Husti ◽  
Khairunnas Jamal ◽  
Afriadi Putra
Keyword(s):  
Social Media ◽  
Law Enforcement ◽  
Quality Of Information ◽  
Media Usage ◽  
Large Group ◽  
Six Elements ◽  
Written Law ◽  
Use Of Social Media ◽  
The Universe

This article aims to explain maqâṣid al-Qur’ân according to M. Quraish Shihab and its application in interpreting verses related to the use of social media. The problem that will be answered in this article covers two main issues, namely how the perspective of maqâṣid al-Qur’ân according to M. Quraish Shihab and how it is applied in interpreting the verses of the use of social media. The method used is the thematic method, namely discussing verses based on themes. Fr om this study the authors concluded that according to M. Quraish Shihab there are six elements of a large group of universal goals of the al-Qur’ân, namely strengthening the faith, humans as caliphs, unifying books, law enforcement, callers to the ummah of wasathan, and mastering world civilization. The quality of information lies in the strength of the monotheistic dimension which is the highest peak of the Qur’anic maqâṣid. M. Quraish Shihab offers six diction which can be done by recipients of information in interacting on social media. Thus, it aims to usher in the knowledge and understanding of what is conveyed in carrying out human mission as caliph, enlightenment through oral and written, law enforcement, unifying mankind and the universe to the ummah of wasathan, and mastery of world civilization

The Use of Social Media by the Botswana Government and Governance of Liquid Communication

Mousaion ◽  
2019 ◽  
Vol 37 (1) ◽  
Author(s):  
Tshepho Lydia Mosweu
Keyword(s):  
Social Media ◽  
Customer Service ◽  
Community Involvement ◽  
Media Content ◽  
Service Access ◽  
Communication Tool ◽  
African Countries ◽  
The World ◽  
The Government ◽  
Use Of Social Media

Social media as a communication tool has enabled governments around the world to interact with citizens for customer service, access to information and to direct community involvement needs. The trends around the world show recognition by governments that social media content may constitute records and should be managed accordingly. The literature shows that governments and organisations in other countries, particularly in Europe, have social media policies and strategies to guide the management of social media content, but there is less evidence among African countries. Thus the purpose of this paper is to examine the extent of usage of social media by the Botswana government in order to determine the necessity for the governance of liquid communication. Liquid communication here refers to the type of communication that goes easily back and forth between participants involved through social media. The ARMA principle of availability requires that where there is information governance, an organisation shall maintain its information assets in a manner that ensures their timely, efficient and accurate retrieval. The study adopted a qualitative case study approach where data were collected through documentary reviews and interviews among purposively selected employees of the Botswana government. This study revealed that the Botswana government has been actively using social media platforms to interact with its citizens since 2011 for increased access, usage and awareness of services offered by the government. Nonetheless, the study revealed that the government had no official documentation on the use of social media, and policies and strategies that dealt with the governance of liquid communication. This study recommends the governance of liquid communication to ensure timely, efficient and accurate retrieval when needed for business purposes.

Social Media Use and Students’ Health-Lifestyle Modification in University of Calabar, Nigeria

2019 ◽  
Vol 5 (1) ◽  
pp. 47
Author(s):  
Ntongha Eni Ikpi ◽  
Veronica Akwenabuaye Undelikwo
Keyword(s):  
Social Media ◽  
Undergraduate Students ◽  
Lifestyle Modification ◽  
Media Use ◽  
Survey Design ◽  
Health Sector ◽  
Positive Health ◽  
Social Media Use ◽  
Health Lifestyle ◽  
Use Of Social Media

The use of social media platforms has over the years become a veritable tool for individuals, groups, institutions and corporate bodies for the promotion of health and wellness. In recent times, social media has become one of the most potent agents of the media through which health issues are addressed as well as generated and disseminated to different populations in society. The study was conducted to examine social media use and students’ health lifestyle modification in the University of Calabar, Nigeria. It sought to determine the extent to which students’ use of social media (Facebook, Twitter, and WhatsApp) influences the modification of their health-related lifestyles such as eating habits, sexual behaviour, cigarette and alcohol consumption, drug use and the engagement in fitness activities. The study adopted a randomized descriptive survey design and used a sample of 300 undergraduate students. The questionnaire was the main instrument used for collection of data while simple percentages and means were used to determine the difference between the expected mean of 2.50 and the observed means across various items in the questionnaire. The results showed that apart from Twitter, social media use by University of Calabar students has significantly influenced the modification of their health lifestyles. Since social media has become a veritable tool for the promotion of positive health lifestyle, effort should be made by government through the health sector to create more awareness among students and the entire population of social media users, on the health benefits accruing from use of social media.

Sign in / Sign up

Export Citation Format

Share Document