According to a March 2024 survey conducted in the United States, 32 percent of adults reported feeling that social media had neither a positive nor negative effect on their own mental health. Only seven percent of social media users said that online platforms had a very positive effect on their mental health, while 12 percent of users said it had a very negative impact. Furthermore, 22 percent of respondents said social media had a somewhat negative effect on their mental health. Is social media addictive? A 2023 survey of individuals between 11 and 59 years old in the United States found that over 73 percent of TikTok users agreed that the platform was addictive. Furthermore, nearly 27 percent of those surveyed reported experiencing negative psychological effects related to TikTok use. Users belonging to Generation Z were the most likely to say that TikTok is addictive, yet millennials felt the negative effects of using the app more so than Gen Z. In the U.S., it is also not uncommon for social media users to take breaks from using online platforms, and as of March 2024, over a third of adults in the country had done so. Following mental health-related content Although online users may be aware of the negative and addictive aspects of social media, it is also a useful tool for finding supportive content. In a global survey conducted in 2023, 32 percent of social media users followed therapists and mental health professionals on social media. Overall, 24 percent of respondents said that they followed people on social media if they had the same condition as they did. Between January 2020 and March 2023, British actress and model Cara Delevingne was the celebrity mental health activist with the highest growth in searches tying her name to the topic.

This statistic illustrates the share of internet users in the United States who have had negative experiences as a result from being active on social media. According to the August 2017 survey, 71 percent of respondents had felt offended by posts, comments, or pictures they had seen on social media.

A survey conducted in 2022 found that 23 percent of teenagers in the United States who felt negatively impacted by social media reported having concerns about the amount of time they spent on such services. Furthermore, 22 percent of teens in the country said that social media negatively impacted them because of its potential negative effects on mental health.

90% of people aged 18-29 use social media in some form. 15% of people aged 23-38 admit that they are addicted to social media.

Facebook and YouTube are still the most used social media platforms today.

More than five out of 10 teenagers in Poland could not last without using social media for several hours in 2022. Nearly 40 percent of those surveyed said they could go without using social media for a week or more.

These are the key social media statistics that you need to know.

While work on the relationship between social media use and adolescent mental health has allowed for some progress, research in this area is still relatively new and shows mixed evidence. This is partly the consequence of a rapidly changing field, resulting in conceptualisation and measurement issues that hinder progress. Given the need for robust conceptualisation, the present study included five focus groups with a total of 26 adolescents aged 11-15 in Northwest England, to understand their experiences, motivations, and perceptions of social media use, relating to mental health and wellbeing. Reflexive thematic analysis was used to analyse the transcripts. We developed three themes and 14 sub-themes. Young people discussed key motivations for using social media (theme 1) relating to social connections, keeping up-to-date, mood management, the ‘default’ activity, freedom to express and develop myself, and fitting in. They shared some of the benefits and positive experiences of social media use (theme 2) such as feeling connected, validation and reassurance, and enjoyment and supporting a sense of self, and finally, they talked about negative experiences of social media use (theme 3), including platform risks, loss of control, social conflict, social comparison, and self-presentation management. Our findings have contributed to our understanding of the salient dimensions and language to inform the development of an adolescent social media experience measure related to mental health.

The increased use of social media among young people has attracted the attention of the public, the media and the government, and has led to growing concerns about its impact on young people's mental health, wellbeing and levels of loneliness. This concern stems from reported increase in mental health difficulties and increased social media use among this population. Research on this area is however relatively new and with mixed evidence. While some of the experiences with social media can be challenging, there is not sufficient evidence to support that social media is fundamentally bad. Indeed, recent evidence challenges this and suggests that the connection between social media and mental health might be a weak one, and its benefits, that have been largely overlooked, should also be considered.

This area of research has suffered the consequences of a rapidly changing field, resulting in quick, but methodologically flawed self-report measures of social media experience, that hinders progress. We have identified three potential problems in the self-report measurement of social media engagement and experience:

1) Most measures were developed without asking young people's experiences. This means that social media measures are being developed for young people without young people having any input. How can we be sure we are asking the right things if we do not consider their views?; 2) Many measures focus on "addictive social media", however this term is based largely on anecdotal evidence. In fact, the questions they use in these measures are based on nicotine dependence and gambling addiction criteria. Assuming these are the same can lead to misleading conclusions; 3) Many of the existing measures were not developed using rigorous and robust theoretical and statistical (psychometric) methods. Their validity is therefore questionable; 4) Even though the engagement with social media includes objective digital behaviours, this kind of information and data have not been considered during the development of measures. We cannot capture however the full picture of social media experience without assessing both, because they each offer unique information.

To address these challenges and limitations reported in the current literature we propose a 3-year project to co-develop, with young people, a comprehensive and freely available self-report social media experience measure that will be appropriate for young people. This will take into account existing research, objective social media data, and the views of social media experts, clinicians, parents/carers, teachers, and policy makers. Importantly, the development of the measure will be guided by the views and experiences of young people.

The proposed project will follow a novel method that combines traditional methods of scale development and a novel approach that triangulates objective (e.g. online social media comments) and subjective (e.g. self-report) assessment. The current project has a strong focus on the voices of young people and it will be based on a co-production model with young people. We will draw from different disciplines including digital behaviour and social media, mental health, loneliness, psychometrics, and computer science. The project has the potential to improve the way we measure, and therefore understand, young people's social media experience and how that influences their mental health, wellbeing, and loneliness. It will also provide a...

Global ad spend were expected to reach over $134 billion in 2022. This means that it has increased by over 17% yearly.

An online survey conducted in November 2023 in the United States found that 56 percent of internet users aged 18 to 29 years thought that social media was a good thing for society. In contrast, 22 percent of respondents between 30 and 44 years felt that social media had a bad impact on society, as did 38 percent of those aged 45 to 64. Overall, only 12 percent of survey respondents aged 65 years and over thought that social media was a good thing for society.

59% of adults in the united states are using Instagram daily.

The average Facebook user spends about 19.6 per month on Facebook every month. This works out to be about 39 minutes per day.

Problem Statement

👉 Download the case studies here

A global consumer goods company struggled to understand customer sentiment across various social media platforms. With millions of posts, reviews, and comments generated daily, manually tracking and analyzing public opinion was inefficient. The company needed an automated solution to monitor brand perception, address negative feedback promptly, and leverage insights for marketing strategies.

Challenge

Analyzing social media sentiment posed the following challenges:

Processing vast amounts of unstructured text data from multiple platforms like Twitter, Facebook, and Instagram.

Accurately interpreting slang, emojis, and nuanced language used by social media users.

Identifying trends and actionable insights in real-time to respond to potential crises or opportunities effectively.

Solution Provided

An advanced sentiment analysis system was developed using Natural Language Processing (NLP) and sentiment analysis algorithms. The solution was designed to:

Classify social media posts into positive, negative, and neutral sentiments.

Extract key topics and trends related to the brand and its products.

Provide real-time dashboards for monitoring customer sentiment and identifying areas of improvement.

Development Steps

Data Collection

Aggregated data from major social media platforms using APIs, focusing on brand mentions, hashtags, and product keywords.

Preprocessing

Cleaned and normalized text data, including handling slang, emojis, and misspellings, to prepare it for analysis.

Model Training

Trained NLP models for sentiment classification using supervised learning. Implemented topic modeling algorithms to identify recurring themes and discussions.

Validation

Tested the sentiment analysis models on labeled datasets to ensure high accuracy and relevance in classifying social media posts.

Deployment

Integrated the sentiment analysis system with a real-time analytics dashboard, enabling the marketing and customer support teams to track trends and respond proactively.

Monitoring & Improvement

Established a continuous feedback mechanism to refine models based on evolving language patterns and new social media trends.

Results

Gained Actionable Insights

The system provided detailed insights into customer opinions, helping the company identify strengths and areas for improvement.

Improved Brand Reputation Management

Real-time monitoring enabled swift responses to negative feedback, mitigating potential reputation risks.

Informed Marketing Strategies

Insights from sentiment analysis guided targeted marketing campaigns, resulting in higher engagement and ROI.

Enhanced Customer Relationships

Proactive engagement with customers based on sentiment analysis improved customer satisfaction and loyalty.

Scalable Monitoring Solution

The system scaled efficiently to analyze data across multiple languages and platforms, broadening the company’s reach and understanding.

According to a November 2023 survey of internet users in the United States, 28 percent of responding adults thought that social media was bad for the society. Overall, around one third of respondents thought social media had a good impact on society. Furthermore, 32 percent of respondents answered that it was neither good nor bad.

56.5% of Facebook users worldwide are male. This is in direct contrast to only 43.5% of Facebook being female.

IntroductionThe relationship between students’ smartphone addiction, social media use, video games play, and their academic performance has been widely studied, yet the existing literature presents inconsistent findings. This meta-analysis synthesizes current research to provide a comprehensive examination of the impact of these technologies on academic achievement.MethodsA total of 63 studies (yielding 64 effect sizes) were included, encompassing a sample of 124,166 students from 28 countries. The meta-analysis utilized correlation coefficients and sample sizes, reporting results based on the random effects model. Key statistics such as the Fisher’s Z value, confidence intervals, and heterogeneity (Q) test results were considered, and publication bias was assessed using Begg and Mazumdar’s rank correlation test, with the Kendall Tau coefficient determining bias significance.Results and discussionThe meta-analysis revealed a small but statistically significant negative association between smartphone use, social media use, video game playing, and students’ academic performance [Q(64) = 2501.93, p 

According to a global survey conducted in 2021, heavier social media users felt more strongly about the effects of social media on social wellbeing. Overall, 33 percent of respondents who spent more than three hours per day on social media said that usage of such online platforms negatively impacted social wellbeing such as not feeling close to others or not being part of a supportive community. In contrast, of respondents who spent just one hour per day on social media, only 20 percent felt that social media harmed social wellbeing.

Facebook is fast approaching 3 billion monthly active users. That’s about 36% of the world’s entire population that log in and use Facebook at least once a month.

General Description

This dataset comprises 4,038 tweets in Spanish, related to discussions about artificial intelligence (AI), and was created and utilized in the publication "Enhancing Sentiment Analysis on Social Media: Integrating Text and Metadata for Refined Insights," (10.1109/IE61493.2024.10599899) presented at the 20th International Conference on Intelligent Environments. It is designed to support research on public perception, sentiment, and engagement with AI topics on social media from a Spanish-speaking perspective. Each entry includes detailed annotations covering sentiment analysis, user engagement metrics, and user profile characteristics, among others.

Data Collection Method

Tweets were gathered through the Twitter API v1.1 by targeting keywords and hashtags associated with artificial intelligence, focusing specifically on content in Spanish. The dataset captures a wide array of discussions, offering a holistic view of the Spanish-speaking public's sentiment towards AI.

Dataset Content

• ID: A unique identifier for each tweet.
• text: The textual content of the tweet. It is a string with a maximum allowed length of 280 characters.
• polarity: The tweet's sentiment polarity (e.g., Positive, Negative, Neutral).
• favorite_count: Indicates how many times the tweet has been liked by Twitter users. It is a non-negative integer.
• retweet_count: The number of times this tweet has been retweeted. It is a non-negative integer.
• user_verified: When true, indicates that the user has a verified account, which helps the public recognize the authenticity of accounts of public interest. It is a boolean data type with two allowed values: True or False.
• user_default_profile: When true, indicates that the user has not altered the theme or background of their user profile. It is a boolean data type with two allowed values: True or False.
• user_has_extended_profile: When true, indicates that the user has an extended profile. An extended profile on Twitter allows users to provide more detailed information about themselves, such as an extended biography, a header image, details about their location, website, and other additional data. It is a boolean data type with two allowed values: True or False.
• user_followers_count: The current number of followers the account has. It is a non-negative integer.
• user_friends_count: The number of users that the account is following. It is a non-negative integer.
• user_favourites_count: The number of tweets this user has liked since the account was created. It is a non-negative integer.
• user_statuses_count: The number of tweets (including retweets) posted by the user. It is a non-negative integer.
• user_protected: When true, indicates that this user has chosen to protect their tweets, meaning their tweets are not publicly visible without their permission. It is a boolean data type with two allowed values: True or False.
• user_is_translator: When true, indicates that the user posting the tweet is a verified translator on Twitter. This means they have been recognized and validated by the platform as translators of content in different languages. It is a boolean data type with two allowed values: True or False.

Cite as

Guerrero-Contreras, G., Balderas-Díaz, S., Serrano-Fernández, A., & Muñoz, A. (2024, June). Enhancing Sentiment Analysis on Social Media: Integrating Text and Metadata for Refined Insights. In 2024 International Conference on Intelligent Environments (IE) (pp. 62-69). IEEE.

Potential Use Cases

This dataset is aimed at academic researchers and practitioners with interests in:

• Sentiment analysis and natural language processing (NLP) with a focus on AI discussions in the Spanish language.
• Social media analysis on public engagement and perception of artificial intelligence among Spanish speakers.
• Exploring correlations between user engagement metrics and sentiment in discussions about AI.

Data Format and File Type

The dataset is provided in CSV format, ensuring compatibility with a wide range of data analysis tools and programming environments.

License

The dataset is available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license, permitting sharing, copying, distribution, transmission, and adaptation of the work for any purpose, including commercial, provided proper attribution is given.

Researcher(s): Alexandros Mokas, Eleni Kamateri

Supervisor: Ioannis Tsampoulatidis

This repository contains 3 social media datasets:

2 Post-processing datasets: These datasets contain post-processing data extracted from the analysis of social media posts collected for two different use cases during the first two years of the Deepcube project. More specifically, these include:

• The UC2 dataset containing the post-processing analysis of the Twitter data collected for the DeepCube use case (UC2) dealing with the climate induced migration in Africa. This dataset contains in total 5,695,253 social media posts collected from the Twitter platform, based on the initial version of search criteria relevant to UC2 defined by Universitat De Valencia, focused on the regions of Ethiopia and Somalia and started from 26 June, 2021 till March, 2023.
• The UC5 dataset containing the post-processing analysis of the Twitter and Instagram data collected for the DeepCube use case (UC5) related to the sustainable and environmentally-friendly tourism. This dataset contains in total 58,143 social media posts collected from the Twitter and Instagram platform (12,881 collected from Twitter and 45,262 collected from Instagram), based on the initial version of search criteria relevant to UC5 defined by MURMURATION SAS, focused on the regions of Brasil and started from 26 June, 2021 till March, 2023.

1 Annotated dataset: An additional anottated dataset was created that contains post-processing data along with annotations of Twitter posts collected for UC2 for the years 2010-2022. More specifically, it includes:

• The UC2 dataset contain the post-processing of the Twitter data collected for the DeepCube use case (UC2) dealing with the climate induced migration in Africa. This dataset contains in total 1721 annotated (412 relevant and 1309 irrelevant) by social media posts collected from the Twitter platform, focused on the region of Somalia and started from 1 January, 2010 till 31 December, 2022.

For every social media post retrieved from Twitter and Instagram, a preprocessing step was performed. This involved a three-step analysis of each post using the appropriate web service. First, the location of the post was automatically extracted from the text using a location extraction service. Second, the images included in the post were analyzed using a concept extraction service, which identified and provided the top ten concepts that best described the image. These concepts included items such as "person," "building," "drought," "sun," and so on. Finally, the sentiment expressed in the post's text was determined by using a sentiment analysis service. The sentiment was classified as either positive, negative, or neutral.

After the social media posts were preprocessed, they were visualized using the Social Media Web Application. This intuitive, user-friendly online application was designed for both expert and non-expert users and offers a web-based user interface for filtering and visualizing the collected social media data. The application provides various filtering options, an interactive map, a timeline, and a collection of graphs to help users analyze the data. Moreover, this application provides users with the option to download aggregated data for specific periods by applying filters and clicking the "Download Posts" button. This feature allows users to easily extract and analyze social media data outside of the web application, providing greater flexibility and control over data analysis.

The dataset is provided by INFALIA.

INFALIA, being a spin-off of the CERTH institute and a partner of a research EU project, releases this dataset containing Tweets IDs and post pre-processing data for the sole purpose of enabling the validation of the research conducted within the DeepCube. Moreover, Twitter Content provided in this dataset to third parties remains subject to the Twitter Policy, and those third parties must agree to the Twitter Terms of Service, Privacy Policy, Developer Agreement, and Developer Policy (https://developer.twitter.com/en/developer-terms) before receiving this download.