Matching Marathon Bombers’ Name Misspellings and Name Variants

It has been a tough few weeks for Boston. Many of us here at Basis Technology know of someone who was directly affected by the marathon bombings. Our Cambridge office was closed during the lockdown last Friday while events played out just a mile or two away.

As the media uncovers new information, seemingly by the hour, it is clear that spelling variations in the Tsarnaev brothers’ names was a major roadblock towards the goal of “Preventative Intelligence.” Individual spelling or transliteration variants of the name have cropped up in English and Russian news reports and even passenger logs, illustrating how difficult the name resolution challenge is to solve.

“The reason we didn’t know he went to Russia is because the name was misspelled,” said Sen. Lindsey Graham regarding the FBI investigation of Tamerlan Tsarnaev. While it is not clear if this was a typo or a deliberate alias, Tsarnaev has also been represented as Царнаев and transliterated as Carnaev, or czarnaev amongst others.

Here at Basis Technology, we are on a mission to solve this problem. Our Rosette Name Indexer (RNI) resolves names to their likely matches across many language variations. The resulting, newly uncovered information can be used to flag an individual from a watch list or simply log pertinent details to the correct identity, enabling law enforcement officials to prevent these events in the future.

To illustrate the power of RNI, we ran a test using the many spellings and name variations identifying the elder Tsarnaev brother found in both local and international news reports. As you can see in the chart below, Name Indexer provides the “similarity” scores for each potential recognized name, giving officials a powerful weapon in this ongoing battle.