Digital Diet

Name: Digital Diet
Author: Massachusetts Institute of Technology

Massachusetts Institute of Technology

VALIDATED

Proven effective in research studies

For:General Public & Enthusiasts

Free

Download on the App Store Get it on Google Play

App Summary

Digital Diet is a web-browsing tool designed to help users understand their online information habits by labeling content based on its emotional tone, actionability, and potential to increase knowledge. An evaluation based on four studies (N=1,145) found a causal link where browsing negative content worsens mood, and showed that an intervention highlighting a webpage's emotional impact reduced negative browsing and improved mood. The authors conclude that altering web-browsing patterns can break self-reinforcing negative feedback loops, providing a potential method for enhancing well-being in the digital age.

App Screenshots

Detailed Description

Functionality & Mechanism

Digital Diet operates as a Google Chrome extension linked to a companion application. The system leverages natural language processing and machine learning to analyze webpages surfaced in Google search results. It then overlays quantitative "content labels" that predict a page's Actionability (potential to guide action), Knowledge (capacity to enhance understanding), and emotional Valence. The interface aggregates this data, presenting a dashboard that quantifies information consumption patterns to facilitate more intentional browsing habits and promote digital well-being.

Evidence & Research Context

The tool's design is grounded in research identifying three primary motives for information-seeking: its utility for action, its predicted emotional impact, and its conceptual relevance.
Foundational research across four studies (N=1,145 total) established a causal, bidirectional relationship between browsing negative online information and decrements in mood and mental health.
A related intervention study demonstrated that altering web-browsing patterns by highlighting content's emotional impact effectively reduced negative information consumption and improved participant mood.
The system's classification models were trained on data from human participants to ensure the content labels accurately reflect user perceptions of webpage properties.

Intended Use & Scope

This tool is intended for the general public as a behavioral awareness system to support digital self-regulation. Its primary utility is providing quantitative feedback on web-browsing habits to help individuals align online activity with personal goals. The system does not provide clinical diagnoses or replace professional mental health treatment. Users concerned about their mental health should consult a qualified clinician for assessment and guidance.

Studies & Publications

3 publications

Peer-reviewed research associated with this app.

Effectiveness/Outcome Study

Web-browsing patterns reflect and shape mood and mental health

Kelly et al. (2024) · Nature Human Behaviour

Intervention successfully changed web-browsing patterns toward more positive content and improved participants' mood.

Humans spend on average 6.5 hours a day online. A large portion of that time is dedicated to information-seeking. How does this activity impact mental health? We assess this over four studies (n = 1,145). We reveal that the valence of information sought affects mental health, which in turn influences the valence of information sought, forming a self-reinforcing loop. We quantified the valence of text on webpages participants chose to browse using natural language processing and found that browsing more negative information was associated with worse mental health and mood. By manipulating the webpages browsed and measuring mood and vice versa, we show that the relationship is causal and bidirectional. Finally, we developed an intervention that altered web-browsing patterns in a manner that improved mood. Together, the findings suggest that the information sought reflects mental state and shapes it, creating a loop that may perpetuate mental health problems. The results also provide a potential method for assessing and enhancing welfare in the digital age. In four studies, Kelly and Sharot reveal that web-browsing both reflects and affects mental health. Poorer mental health leads to more negative content consumption, which in turn worsens mood. Highlighting webpage emotional impacts reduced negative browsing and improved mood.

Development/Design Paper

A Tool to Facilitate Web-Browsing

Kelly et al. (2024) · arXiv

Describes the research-driven development of this app

Search engine results often misalign with users' goals due to opaque algorithms, leading to unhelpful or detrimental information consumption. To address this, we developed a Google Chrome plugin that provides "content labels" for webpages in Google search results, assessing Actionability (guiding actions), Knowledge (enhancing understanding), and Emotion. Using natural language processing and machine learning, the plugin predicts these properties from webpage text based on models trained on participants' ratings, effectively reflecting user perceptions. The implications include enhanced user control over information consumption and promotion of healthier engagement with online content, potentially improving decision-making and well-being.

In the Media

Study: Browsing negative content online makes mental health struggles worse

MIT researchers Tali Sharot and Christopher A. Kelly developed a web plug-in tool to help people protect their mental health by making informed decisions about online content they view. Their study of over 1,000 participants found "a causal, bidirectional relationship between health and what you do online" where people with mental health symptoms browse more negative content, which then worsens their symptoms in "a feedback loop." The findings were published November 21 in the journal Nature Human Behavior.

MITRead article

Poor mental health linked to browsing negative content online

UCL researchers developed Digital Diet to break the cycle of negative online browsing that worsens mental health, using content labels similar to nutrition labels on food that emphasize emotional impact alongside practicality and informativeness. Professor Tali Sharot explained, "Our results show that browsing negatively valenced content not only mirrors a person's mood but can also actively worsen it. This creates a feedback loop that can perpetuate mental health challenges over time." The Wellcome-funded study analyzed over 1,000 participants' browsing habits and was published in Nature Human Behaviour.

AcRead article