Data analytics tools such as those provided by Relativity Analytics play an essential role on many eDiscovery projects. They offer the means to make document review more efficient and accurate, which ultimately saves corporations and law firms time and money. Yet they must be utilized correctly to provide the most benefits. The examples below provide a glimpse into some common practical applications for leveraging Relativity Analytics to improve your review workflows.
Structured Analytics Tools
Structured analytics allow a user to analyze text to identify similarities and differences between documents in a dataset and quickly organize them to help speed up review. These tools include the following:
- Email threading. This is a useful tool for organizing and even removing duplicative content from an email data review. For example, it can help with grouping, sorting, and batching emails by conversation or thread to increase review speeds and coding consistency through a more linear review. It also allows the user to focus review and production on only inclusive, non-duplicative emails, particularly where there is a production agreement in place allowing or mandating it.
- Language Identification. Language identification may be leveraged to quickly parse out what various languages might exist in your workspace, helping flag items for potential additional review and/or translation – whether by machine or human translator. CDS offers translation services to assist with this process as well.
- Textual Near Duplicate Identification. One of the benefits of textual near duplicate identification is that it can help fill the gap when deduplication is not possible, whether due to processing errors, formatting issues, or other hurdles. It can be used to identify documents which share enough similarity based on user threshold inputs, and even pinpoint exact textual duplicates. This feature can also be used for grouping documents with similar content for streamlined review, or identifying items with high likelihood of needing specific coding based on similar near-duplicates.
- Repeated Content Identification. This is useful when irrelevant or less relevant repetitive text content, such as email footers (based on user inputs), clouds conceptual analytics index results. Once identified, such repeated content excerpts can be actively suppressed from the conceptual index used for any conceptual analytics operations. It can also be used to identify specific documents with repeated content so appropriate measures can be taken to avoid over-inclusive and unhelpful search results. For example, we worked with one client to remove repeated content from specific documents in order to re-build an existing dtSearch index without irrelevant text like email footers, which were returning numerous false search hits.
Conceptual Analytics Tools
Conceptual analytics help the user organize and assess the semantic content of large, diverse and/or unknown sets of documents. These tools include:
- Clustering. Clustering identifies and creates groups of documents with similar text concepts. It even offers an interactive visualization tool for gleaning a quick overview of concepts in your data and drilling deeper into specific concepts on an ad hoc basis. This tool can be especially helpful in retrieving more insight than offered by near duplicate identification, and allows searching or batching by concept groups to help further streamline review. Sorting in tandem with email threading can also add an additional layer of organization and efficiency.
- Categorization. This takes things one step further and may be leveraged to find and categorize documents that share similar concepts (even more than one), based on a subset of previously coded sample documents. Categorization also ranks results by similarity, allowing quick, easy organization, prioritization, and even coding of (e.g., most likely responsive, privileged, key, etc.) documents for review.
Data analytics tools offer significant opportunities to improve workflows and streamline document review, but eDiscovery experts can provide guidance on how and when to use these tools for the best outcome. Contact CDS to learn how our suite of Analytics tools can assist you in your next matter.