New
(2025) AI Processed Human Approved
The Impact of Cyberbullying on Help-Seeking Among Depressed Young adults in the United States
This study utilized a mixed-methods design integrating qualitative content analysis and text mining to explore cyberbullying behaviors on TikTok. The researcher analyzed 83,154 comments across 50 TikTok videos featuring young adults in the United States sharing depressive experiences. The study aimed to evaluate the prevalence, interaction styles, key topics, and overall audience sentiment related to online mental health disclosures.
Problem
While social media platforms like TikTok have become primary outlets for young adults to disclose mental health struggles, online harassment creates severe barriers to seeking professional help. A critical knowledge gap exists regarding platform-specific cyberbullying dynamics on TikTok and how hostile interactions affect vulnerable youth experiencing depression in the United States.
Outcome
- Non-cyberbullying comments significantly outnumbered cyberbullying comments, accounting for 92.2% of overall engagement compared to 7.8% cyberbullying interactions.
- Supportive responses were the most common interaction style (53.51%), followed by harmful (17.68%), dismissive (15.91%), sarcastic (8.83%), peer invalidation (3.42%), and blaming (0.65%) comments.
- Sentiment analysis revealed that responses to depression-related content were predominantly neutral, reflecting cautious and non-judgmental user engagement.
- Topic modeling identified five primary thematic areas in user discussions: Emotional Vulnerability, Identity Struggles, Social Connection, Negative Emotions, and Emotional Expression.
- Supportive responses were the most common interaction style (53.51%), followed by harmful (17.68%), dismissive (15.91%), sarcastic (8.83%), peer invalidation (3.42%), and blaming (0.65%) comments.
- Sentiment analysis revealed that responses to depression-related content were predominantly neutral, reflecting cautious and non-judgmental user engagement.
- Topic modeling identified five primary thematic areas in user discussions: Emotional Vulnerability, Identity Struggles, Social Connection, Negative Emotions, and Emotional Expression.
What it means for you
- CIO / IT Executive: On Monday morning, direct your cybersecurity team to review existing platform moderation tools and policies for social media platforms commonly used by young adults, with a specific focus on identifying potential enhancements to detect and flag harmful comment patterns identified in the research (e.g., dismissive, sarcastic, peer invalidation).
- IT Manager: On Monday morning, initiate a review of our internal IT support resources and documentation related to online safety and responsible social media use, ensuring it includes guidance on identifying and reporting cyberbullying, and consider adding specific examples of the types of harmful comments found in the research.
- Business Strategist: On Monday morning, task your market research team to analyze the brand's current social media engagement strategy on platforms like TikTok, specifically looking for opportunities to amplify supportive and positive content in response to mental health disclosures, and to identify potential risks associated with negative comment trends.
- Researcher: On Monday morning, begin planning your next research project by drafting a proposal to replicate this study's methodology on other emerging social media platforms or with different demographic groups to broaden the understanding of cyberbullying's impact on help-seeking behavior.
- Policymaker: On Monday morning, schedule a meeting with your legislative aides to begin drafting policy recommendations that encourage social media platforms to implement more robust content moderation systems specifically designed to identify and mitigate cyberbullying that hinders vulnerable individuals from seeking help.
Transcript
Host: Welcome to A.I.S. Insights — powered by Living Knowledge. I'm your host, Anna Ivy Summers.
Expert: And I'm Alex Ian Sutherland. Great to be here, Anna.
Host: Today, we're diving into a crucial new study titled "The Impact of Cyberbullying on Help-Seeking Among Depressed Young adults in the United States." Alex, this study examines how young adults express mental health struggles on social media, specifically TikTok, and what kind of feedback they receive. What's the broader problem driving this research?
Expert: Anna, youth mental health in the U.S. has reached a crisis level. Over 20% of young adults aged 18 to 25 experienced a major depressive episode in 2022 alone. The economic burden of mental health issues is massive, estimated at over 282 billion dollars annually. At the same time, platforms like TikTok have become the de facto public square where young people seek peer support, with over 82% of Gen Z maintaining accounts. But there's a serious concern that hostile comments and cyberbullying on these platforms create psychological barriers, preventing vulnerable youth from seeking professional help.
Host: That makes understanding platform dynamics essential. How did the author go about investigating this on TikTok?
Expert: The study used a powerful mixed-methods approach. The researcher collected 83,154 user comments across 50 TikTok videos where U.S. adolescent girls and young adults disclosed depressive symptoms or sought support. They combined inductive qualitative coding with large-scale text mining in R. This included sentiment analysis and Latent Dirichlet Allocation, or LDA topic modeling, to categorize both the specific interaction styles and the overall emotional climate in the comment sections.
Host: That is a substantial dataset. What were the most striking findings when the text mining results came in?
Expert: The most encouraging finding was that non-cyberbullying comments overwhelmingly dominated engagement, accounting for 92.2% of all comments, while cyberbullying made up just 7.8%. Furthermore, when looking at specific interaction tactics used, supportive comments were actually the most frequent at 53.5%. Harmful comments made up 17.7%, dismissive responses were 15.9%, sarcasm was 8.8%, peer invalidation was 3.4%, and direct blaming was less than 1%.
Host: That’s a fascinating contrast to the idea that comment sections are purely toxic. What about the overall sentiment and topics being discussed?
Expert: Sentiment analysis revealed that audience responses were predominantly neutral, followed by negative sentiment, with positive sentiment being the smallest proportion. Users often adopt a cautious, non-judgmental tone because they aren't sure how to respond to heavy emotional disclosures. As for topics, LDA modeling identified five distinct thematic areas: Emotional Vulnerability, Identity Struggles, Social Connection, Negative Emotions, and Emotional Expression.
Host: Now, let's translate this for our business and technology leaders. Why do these findings matter for platform operators, tech executives, and policymakers?
Expert: There are three critical takeaways for business and tech. First is regulatory compliance. Legislation like the Kids Online Safety Act, or KOSA, is pushing social media companies toward a strict duty of care to protect minors from cyberbullying and mental health harms. This study gives platforms empirical data on what specific harm patterns look like on feed-based video applications.
Host: And second?
Expert: Second is optimizing AI-driven content moderation. Instead of relying on blunt keyword blocks, platforms can train specialized machine learning models—like Convolutional Neural Networks, which achieve up to 95% accuracy—on these exact harassment patterns, such as peer invalidation or sarcasm, to filter toxic content faster without censoring authentic peer support.
Host: And the third point?
Expert: Third is user retention and platform trust. Gen Z makes up a massive share of digital consumers. Creating safer, moderation-backed online communities fosters user trust and protects brand equity. When platform environments support healthy digital citizenship, user engagement becomes more sustainable, benefiting both public health and the platform's bottom line.
Host: It's clear that data-backed moderation strategies can turn regulatory obligations into real platform value while protecting vulnerable users. Alex, thank you for breaking down this vital study for us today.
Expert: My pleasure, Anna.
Host: And thank you to our listeners for tuning into A.I.S. Insights — powered by Living Knowledge. Until next time, stay informed and stay ahead.
Expert: And I'm Alex Ian Sutherland. Great to be here, Anna.
Host: Today, we're diving into a crucial new study titled "The Impact of Cyberbullying on Help-Seeking Among Depressed Young adults in the United States." Alex, this study examines how young adults express mental health struggles on social media, specifically TikTok, and what kind of feedback they receive. What's the broader problem driving this research?
Expert: Anna, youth mental health in the U.S. has reached a crisis level. Over 20% of young adults aged 18 to 25 experienced a major depressive episode in 2022 alone. The economic burden of mental health issues is massive, estimated at over 282 billion dollars annually. At the same time, platforms like TikTok have become the de facto public square where young people seek peer support, with over 82% of Gen Z maintaining accounts. But there's a serious concern that hostile comments and cyberbullying on these platforms create psychological barriers, preventing vulnerable youth from seeking professional help.
Host: That makes understanding platform dynamics essential. How did the author go about investigating this on TikTok?
Expert: The study used a powerful mixed-methods approach. The researcher collected 83,154 user comments across 50 TikTok videos where U.S. adolescent girls and young adults disclosed depressive symptoms or sought support. They combined inductive qualitative coding with large-scale text mining in R. This included sentiment analysis and Latent Dirichlet Allocation, or LDA topic modeling, to categorize both the specific interaction styles and the overall emotional climate in the comment sections.
Host: That is a substantial dataset. What were the most striking findings when the text mining results came in?
Expert: The most encouraging finding was that non-cyberbullying comments overwhelmingly dominated engagement, accounting for 92.2% of all comments, while cyberbullying made up just 7.8%. Furthermore, when looking at specific interaction tactics used, supportive comments were actually the most frequent at 53.5%. Harmful comments made up 17.7%, dismissive responses were 15.9%, sarcasm was 8.8%, peer invalidation was 3.4%, and direct blaming was less than 1%.
Host: That’s a fascinating contrast to the idea that comment sections are purely toxic. What about the overall sentiment and topics being discussed?
Expert: Sentiment analysis revealed that audience responses were predominantly neutral, followed by negative sentiment, with positive sentiment being the smallest proportion. Users often adopt a cautious, non-judgmental tone because they aren't sure how to respond to heavy emotional disclosures. As for topics, LDA modeling identified five distinct thematic areas: Emotional Vulnerability, Identity Struggles, Social Connection, Negative Emotions, and Emotional Expression.
Host: Now, let's translate this for our business and technology leaders. Why do these findings matter for platform operators, tech executives, and policymakers?
Expert: There are three critical takeaways for business and tech. First is regulatory compliance. Legislation like the Kids Online Safety Act, or KOSA, is pushing social media companies toward a strict duty of care to protect minors from cyberbullying and mental health harms. This study gives platforms empirical data on what specific harm patterns look like on feed-based video applications.
Host: And second?
Expert: Second is optimizing AI-driven content moderation. Instead of relying on blunt keyword blocks, platforms can train specialized machine learning models—like Convolutional Neural Networks, which achieve up to 95% accuracy—on these exact harassment patterns, such as peer invalidation or sarcasm, to filter toxic content faster without censoring authentic peer support.
Host: And the third point?
Expert: Third is user retention and platform trust. Gen Z makes up a massive share of digital consumers. Creating safer, moderation-backed online communities fosters user trust and protects brand equity. When platform environments support healthy digital citizenship, user engagement becomes more sustainable, benefiting both public health and the platform's bottom line.
Host: It's clear that data-backed moderation strategies can turn regulatory obligations into real platform value while protecting vulnerable users. Alex, thank you for breaking down this vital study for us today.
Expert: My pleasure, Anna.
Host: And thank you to our listeners for tuning into A.I.S. Insights — powered by Living Knowledge. Until next time, stay informed and stay ahead.