Social Media Image Recognition for Food Trend Analysis

2017 ◽  
Author(s):  
Giuseppe Amato ◽  
Paolo Bolettieri ◽  
Vinicius Monteiro de Lira ◽  
Cristina Ioana Muntean ◽  
Raffaele Perego ◽  
...  
Keyword(s):  
Social Media ◽  
Trend Analysis ◽  
Image Recognition ◽  
Media Image

scholarly journals Teen Girls’ Experiences Negotiating the Ubiquitous Dick Pic: Sexual Double Standards and the Normalization of Image Based Sexual Harassment

Sex Roles ◽  
2021 ◽  
Author(s):  
Jessica Ringrose ◽  
Kaitlyn Regehr ◽  
Sophie Whitehead
Keyword(s):  
Social Media ◽  
Sexual Harassment ◽  
Focus Group Interviews ◽  
Double Standards ◽  
Media Image ◽  
Image Sharing ◽  
Social Currency ◽  
Social Media Platforms ◽  
Group Interviews ◽  
Sexual Double Standards

AbstractA range of important studies have recently explored adult women’s experiences of receiving unwanted dick pics (Amundsen, 2020). However, to date there has been limited research that has explored teen girls’ experiences of receiving unwanted penis images in depth. To address this gap we draw upon our findings from a qualitative study using focus group interviews and arts based drawing methods to explore social media image sharing practices with 144 young people aged 11–18 in seven secondary schools in England. We argue that being bombarded with unwanted dick pics on social media platforms like Snapchat normalises harassing practices as signs of desirability and popularity for girls, but suggest that being sent unsolicited dick pics from boys at school is more difficult for girls to manage or report than ignoring or blocking random older senders. We also found that due to sexual double standards girls were not able to leverage dick pics for status in the same way boys can use girls’ nudes as social currency, since girls faced the possibility of being shamed for being known recipients of dick pics. Finally we explore how some girls challenge abusive elements of toxic masculinity in the drawing sessions and our conclusion argues that unwanted dick pics should always be understood as forms of image based sexual harassment.

MEDIATED INTERACTION RITUALS: A GEOGRAPHY OF EVERYDAY LIFE AND CONTENTION IN BLACK LIVES MATTER*

2020 ◽  
Vol 25 (3) ◽  
pp. 295-313
Author(s):  
Sander van Haperen ◽  
Justus Uitermark ◽  
Alex van der Zeeuw
Keyword(s):  
Social Media ◽  
Everyday Life ◽  
Image Recognition ◽  
Urban Areas ◽  
Interaction Ritual ◽  
Black Lives Matter ◽  
Geographically Dispersed ◽  
Interaction Rituals ◽  
Ritual Theory ◽  
Different Types

The Movement for Black Lives has connected millions of people online. How are their outrage and hope mediated through social media? To address this question, this article extends Randall Collins’s Interaction Ritual Theory to social media. Employing semisupervised image recognition methods on a million Instagram posts with the hashtag #blacklivesmatter, we identify four different interaction ritual types, each with distinct geographies. Instagram posts featuring interactions with physical copresence are concentrated in urban areas. We identify two different types of such areas: arenas where contention plays out and milieus where movement identities are affirmed. Instagram posts that do not feature physical copresence are more geographically dispersed. These posts, including memes and selfies, allow people to engage with the movement even when they are not embedded in activist environments. Our analysis helps to understand how different forms of engagement are embedded in particular places and connected through the circulation of social media posts.

scholarly journals Visual Sentiment Analysis on Social Media Data

2021 ◽  
pp. 366-372
Author(s):  
Harshala Bhoir ◽  
K. Jayamalini
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
Social Media Data ◽  
Media Image ◽  
The Social ◽  
Textual Data ◽  
Art Works ◽  
Negative Sentiment ◽  
Media Data

Visual sentiment analysis is the way to automatically recognize positive and negative emotions from images, videos, graphics, stickers etc. To estimate the polarity of the sentiment evoked by images in terms of positive or negative sentiment, most of the state-of-the-art works exploit the text associated to a social post provided by the user. However, such textual data is typically noisy due to the subjectivity of the user which usually includes text useful to maximize the diffusion of the social post. Proposed system will extract and employ an Objective Text description of images automatically extracted from the visual content rather than the classic Subjective Text provided by the user. The proposed System will extract three views visual view, subjective text view and objective text view of social media image and will give sentiment polarity positive, negative or neutral based on hypothesis table.

scholarly journals Detecting Topics and Sentiments of Public Concerns on COVID-19 Vaccines with Social Media Trend Analysis (Preprint)

10.2196/30765 ◽  
2021 ◽  
Author(s):  
Michal Monselise ◽  
Chia-Hsuan Chang ◽  
Gustavo Ferreira ◽  
Rita Yang ◽  
Christopher C. Yang
Keyword(s):  
Social Media ◽  
Trend Analysis ◽  
Public Concerns

scholarly journals Modelling Popularity Dynamics Based on YouTube Viewers and Subscribers

2019 ◽  
Vol 4 (6) ◽  
pp. 1508-1521
Author(s):  
Mohammed Shahid Irshad ◽  
Adarsh Anand ◽  
Marut Bisht
Keyword(s):  
Social Media ◽  
Data Sets ◽  
Quality Of Information ◽  
Media Image ◽  
Alternative Approach ◽  
Popularity Dynamics ◽  
Youtube Videos ◽  
Media Research ◽  
Social Causes

There are plenty of domains as far as research in social media is concerned; Social Network, Video social media, image social media, research/ professional social media and so on. In the present work, we have focused on YouTube which is one of the pioneering amongst video social media. We have modeled the popularity dynamics of YouTube videos based on the information spread amongst the netizens and the number of subscribers for a particular video. An alternative approach to reach to our proposal has also been provided. In practice, the pace of the spread of information might vary because of various reasons such as quality of information, word of mouth, social causes etc. This transformation has been inculcated in the aforesaid modeling and results obtained on the view-count data sets of YouTube videos are very promising.

Sign in / Sign up

Export Citation Format

Share Document