Pedro Szekely

Creates learning tools that understand data semantics, enabling users to easily transform, integrate and analyze data from heterogeneous sources and services.

ISI News

ABC News: Men Take Longer Than Women to Respond to E-Mail

August 25, 2015

Los Angeles affiliate KABC-TV covered research by Farshad Kooti and Kristina Lerman along with colleagues, finding that men take longer than women to respond to emails

Read More

MIT Technology Review: The Social-Network Illusion That Tricks Your Mind

August 15, 2015

Kristina Lerman and colleagues find that social networks can make certain ideas or behavior seem common when they are in fact, rare

Read More

TakePart: Tech's New Tool in the Hunt for Human Traffickers Who Hide in Plain Sight

June 14, 2015

Pedro Alejandro Szekely and Craig Knoblock were featured for the Internet search tool they created to combat human trafficking

Read More
See More Stories »

Feature Story

A Race to Identify Twitter Bots

June 15, 2015

The growing popularity of social media raises all sorts of questions about online security. According to a recent Twitter SEC filing, approximately 8.5 percent of all users on Twitter are bots, or fake accounts used to produce automated posts. While some of these accounts have commercial purposes, others are influence bots used to generate opinions about a certain topic.

Concerned by the future potential of fake social media accounts, DARPA's Social Media in Strategic Communication (SMIC) program held a four-week challenge this February, where several teams competed to identify a set of influence bots on Twitter.

A USC team composed of faculty and graduate students received first place for accuracy and second place for timing. Aram Galstyan, a research associate professor at the USC Viterbi Department of Computer Science and project leader at the USC Information Sciences Institute (ISI), led the victorious Trojans.

"Spamming behavior has evolved," Galstyan said. "Current bots tend to be more human-like, and people have realized that they can be used for propagating certain kind of information, possibly influencing discussions on specific topics."Read More

Meet Our Researchers

Events

Unless otherwise noted, seminars are open to the public.

Sep 04Barret Zoph (USC/ISI)NL SeminarHow Much Information Does a Human Translator Add to the Original? 3:00pm - 4:00pm
Sep 11Guido Zarrella (MITRE)NL SeminarTBA- 9/113:00pm - 4:00pm
Sep 18 Kaveri Thakoor (USC/BRL)NL SeminarExtracting the Most Important Information from Images to Solve Visual Tasks 3:00pm - 4:00pm
See More Events »

Feature Story

A Race to Identify Twitter Bots

June 15, 2015

The growing popularity of social media raises all sorts of questions about online security. According to a recent Twitter SEC filing, approximately 8.5 percent of all users on Twitter are bots, or fake accounts used to produce automated posts. While some of these accounts have commercial purposes, others are influence bots used to generate opinions about a certain topic.

Concerned by the future potential of fake social media accounts, DARPA's Social Media in Strategic Communication (SMIC) program held a four-week challenge this February, where several teams competed to identify a set of influence bots on Twitter.

A USC team composed of faculty and graduate students received first place for accuracy and second place for timing. Aram Galstyan, a research associate professor at the USC Viterbi Department of Computer Science and project leader at the USC Information Sciences Institute (ISI), led the victorious Trojans.

"Spamming behavior has evolved," Galstyan said. "Current bots tend to be more human-like, and people have realized that they can be used for propagating certain kind of information, possibly influencing discussions on specific topics."Read More