Systems and methods for expanding relevant search results in electronic discovery

A system for expanding relevant search results in electronic discovery, the system comprising:

• a clustering module, stored in memory, that creates a file-participant cluster that links a file within a data source to a set of participants that had at least one interaction with the file;
• a comparison module, stored in memory, that determines that the file-participant cluster and at least one other file-participant cluster exceed a threshold level of similarity relative to one another;
• a merging module, stored in memory, that merges, in response to determining that the file-participant cluster and the other file-participant cluster exceed the threshold level of similarity relative to one another, the file-participant cluster and the other file-participant cluster into a merged file-participant cluster such that the merged file-participant cluster identifies files and participants linked to one another by the file-participant cluster and the other file-participant cluster;
• a communication module, stored in memory, that receives, from a user involved in electronic discovery in connection with a lawsuit, a search query to search the data source for files matching one or more search parameters;
• an indexing module, stored in memory, that identifies a set of interaction times that each represent a point in time at which at least one of the participants interacted with at least one of the files linked by the file-participant cluster or the other file-participant cluster;
• a search module, stored in memory, that determines, in response to the search query, that the file linked to the set of participants by the file-participant cluster matches the search parameters;
• wherein the communication module provides, in response to the search query, a search result to the user involved in the electronic discovery, the search result identifying the merged file-participant cluster, wherein the search result comprises an indication of the set of the interaction times at which the participants interacted with at least one of the files linked by the file-participant cluster or the other file-participant cluster;
• at least one physical processor configured to execute the clustering module, the comparison module, the merging module, the communication module, the indexing module, and the search module.

A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

• create a file-participant cluster that links a file within a data source to a set of participants that had at least one interaction with the file;
• determine that the file-participant cluster and at least one other file-participant cluster exceed a threshold level of similarity relative to one another;
• in response to determining that the file-participant cluster and the other file-participant cluster exceed the threshold level of similarity relative to one another, merge the file-participant cluster and the other file-participant cluster into a merged file-participant cluster such that the merged file-participant cluster identifies files and participants linked to one another by the file-participant cluster and the other file-participant cluster;
• receive, from a user involved in electronic discovery in connection with a lawsuit, a search query to search the data source for files matching one or more search parameters;
• identify a set of interaction times that each represent a point in time at which at least one of the participants interacted with at least one of the files linked by the file-participant cluster or the other file-participant cluster;
• determine that the file linked to the set of participants by the file-participant cluster matches the search parameters;
• provide, to the user involved in the electronic discovery, a search result that identifies the merged file-participant cluster, wherein the search result comprises an indication of the set of the interaction times at which the participants interacted with at least one of the files linked by the file-participant cluster or the other file-participant cluster.