London Daily

Focus on the big picture.
Saturday, Oct 04, 2025

LinkedIn is using AI to spot and remove inappropriate user accounts

LinkedIn is using AI to spot and remove inappropriate user accounts

LinkedIn says it is using AI and machine learning to spot accounts containing content that runs afoul of its community guidelines.
Social networks including Facebook, Twitter, and Pinterest tap AI and machine learning systems to detect and remove abusive content, as does LinkedIn. The Microsoft-owned platform -which has over 660 million users, 303 million of whom are active monthly -today detailed its approach to handling profiles containing inappropriate content, which ranges from profanity to advertisements for illegal services.

As software engineer Daniel Gorham explained in a blog post, LinkedIn initially relied on a block list -a set of human-curated words and phrases that ran afoul of its Terms of Service and Community Guidelines -to identify and remove potentially fraudulent accounts. However, maintaining it required a significant amount of engineering effort, and the list tended to handle context rather poorly. (For instance, while the word “escort” was sometimes associated with prostitution, it was also used in contexts like a “security escort” or “medical escort.”)

This motivated LinkedIn to adopt a machine learning approach involving a convolutional neural network -a class of algorithm commonly applied to imagery analysis -trained on public member profile content. The content in question contained accounts labeled as either “inappropriate” or “appropriate,” where the former comprised accounts removed due to inappropriate content as spotted using the block list and a manual review. Gorham notes that only a “very small” portion of accounts have every been restricted in this way, which necessitated downsampling from the entire LinkedIn member base to obtain the “appropriate” labeled accounts and prevent algorithmic bias.

To further tamp down on bias, LinkedIn identified problematic words responsible for high levels of false positives and sampled appropriate accounts from the member base containing these words. The accounts were then manually labeled and added to the training set, after which the model was trained and deployed in production.

Gorham says the abusive account detector scores new accounts daily, and that it was run on the existing member base to identify old accounts containing inappropriate content. Going forward, LinkedIn intends to use Microsoft translation services to ensure consistent performance across all languages, and to refine and expand the training set to increase the scope of content it is able to identify with the model.

“Detecting and preventing abuse on LinkedIn is an ongoing effort requiring extensive collaboration between multiple teams,” wrote Gorham. “Finding and removing profiles with inappropriate content in an effective, scalable manner is one way we’re constantly working to provide a safe and professional platform.”

LinkedIn’s uses of AI extend beyond abusive content detection. In October 2019, it pulled back the curtains on a model that automatically generates text descriptions for images uploaded to LinkedIn, achieved using Microsoft’s Cognitive Services platform and a unique LinkedIn-derived data set. Separately, its Recommended Candidates feature learns the hiring criteria for a given role and automatically surfaces relevant candidates in a dedicated tab. And its AI-driven search engine leverages data such as the kinds of things people post on their profiles and the searches that candidates perform to produce predictions for best-fit jobs and job seekers.
Newsletter

Related Articles

0:00
0:00
Close
Trump Administration Launches “TrumpRx” Plan to Enable Direct Drug Sales at Deep Discounts
Trump Announces Intention to Impose 100 Percent Tariff on Foreign-Made Films
Altman Says GPT-5 Already Outpaces Him, Warns AI Could Automate 40% of Work
Singapore and Hong Kong Vie to Dominate Asia’s Rising Gold Trade
Trump Organization Teams with Saudi Developer on $1 Billion Trump Plaza in Jeddah
Manhattan Sees Surge in Office-to-Housing Conversions, Highest Since 2008
Switzerland and U.S. Issue Joint Assurance Against Currency Manipulation
Electronic Arts to Be Taken Private in Historic $55 Billion Buyout
Thomas Jacob Sanford Named as Suspect in Deadly Michigan Church Shooting and Arson
Russian Research Vessel 'Yantar' Tracked Mapping Europe’s Subsea Cables, Raising Security Alarms
New York Man Arrested After On-Air Confession to 2017 Parents’ Murders
U.S. Defense Chief Orders Sudden Summit of Hundreds of Generals and Admirals
Global Cruise Industry Posts Dramatic Comeback with 34.6 Million Passengers in 2024
Trump Claims FBI Planted 274 Agents at Capitol Riot, Citing Unverified Reports
India: Internet Suspended in Bareilly Amid Communal Clashes Between Muslims and Hindus
Supreme Court Extends Freeze on Nearly $5 Billion in U.S. Foreign Aid at Trump’s Request
Archaeologists Recover Statues and Temples from 2,000-Year-Old Sunken City off Alexandria
China Deploys 2,000 Workers to Spain to Build Major EV Battery Factory, Raising European Dependence
Speed Takes Over: How Drive-Through Coffee Chains Are Rewriting U.S. Coffee Culture
U.S. Demands Brussels Scrutinize Digital Rules to Prevent Bias Against American Tech
Ringo Starr Champions Enduring Beatles Legacy While Debuting Las Vegas Art Show
Private Equity’s Fundraising Surge Triggers Concern of European Market Shake-Out
Colombian President Petro Vows to Mobilize Volunteers for Gaza and Joins List of Fighters
FBI Removes Agents Who Kneeled at 2020 Protest, Citing Breach of Professional Conduct
Trump Alleges ‘Triple Sabotage’ at United Nations After Escalator and Teleprompter Failures
Shock in France: 5 Years in Prison for Former President Nicolas Sarkozy
Tokyo’s Jimbōchō Named World’s Coolest Neighbourhood for 2025
European Officials Fear Trump May Shift Blame for Ukraine War onto EU
BNP Paribas Abandons Ban on 'Controversial Weapons' Financing Amid Europe’s Defence Push
Typhoon Ragasa Leaves Trail of Destruction Across East Asia Before Making Landfall in China
The Personality Rights Challenge in India’s AI Era
Big Banks Rebuild in Hong Kong as Deal Volume Surges
Italy Considers Freezing Retirement Age at 67 to Avert Scheduled Hike
Italian City to Impose Tax on Visiting Dogs Starting in 2026
Arnault Denounces Proposed Wealth Tax as Threat to French Economy
Study Finds No Safe Level of Alcohol for Dementia Risk
Denmark Investigates Drone Incursion, Does Not Rule Out Russian Involvement
Lilly CEO Warns UK Is ‘Worst Country in Europe’ for Drug Prices, Pulls Back Investment
Nigel Farage Emerges as Central Force in British Politics with Reform UK Surge
Disney Reinstates ‘Jimmy Kimmel Live!’ after Six-Day Suspension over Charlie Kirk Comments
U.S. Prosecutors Move to Break Up Google’s Advertising Monopoly
Nvidia Pledges Up to $100 Billion Investment in OpenAI to Power Massive AI Data Center Build-Out
U.S. Signals ‘Large and Forceful’ Support for Argentina Amid Market Turmoil
Nvidia and Abu Dhabi’s TII Launch First AI-&-Robotics Lab in the Middle East
Vietnam Faces Up to $25 Billion Export Loss as U.S. Tariffs Bite
Europe Signals Stronger Support for Taiwan at Major Taipei Defence Show
Indonesia Court Upholds Military Law Amid Concerns Over Expanded Civilian Role
Larry Ellison, Michael Dell and Rupert Murdoch Join Trump-Backed Bid to Take Over TikTok
Trump and Musk Reunite Publicly for First Time Since Fallout at Kirk Memorial
Vietnam Closes 86 Million Untouched Bank Accounts Over Biometric ID Rules
×