As well as preserving history, digital collections play a vital role in making it discoverable for future generations. While most platforms—including Veridian—have traditionally relied on keyword-based search to enable access, user expectations are evolving. With everyday interactions shaped by tools like Google, many now expect more intuitive, context-aware search experiences.

In response to this shift, Veridian is already beta testing the integration of semantic search technology into the platform—enhancing the precision of keyword search with the added power of contextual understanding.

So, what exactly is the difference between keyword and semantic search—and is there still a place for both? As user needs evolve, it’s important to understand how each approach works, where each excels, and how combining them can lead to deeper, more meaningful discoveries within our digital collections.


Keyword search: precision, but with limits

Keyword search relies on exact word matching. It retrieves content that includes the specific terms entered by the user—without interpreting context or intent. This makes it highly effective for targeted searches involving names, dates, or direct quotes—situations where the user knows precisely what they're looking for. However, this precision can also be limiting.

For example, a search for “Impact of 1918 New Zealand influenza pandemic” would return only results containing those exact words. It would miss valuable content that uses different but still highly relevant terminology, such as “Spanish flu”. Additionally, it treats “impact” as a literal term rather than understanding its intended meaning. In this way, keyword search can narrow or even undermine the relevance of the results returned.

Semantic search: smarter, context-aware discovery

Semantic search uses natural language processing and machine learning to interpret the meaning behind a search query—not just the literal words used. Unlike keyword search, which looks for exact matches, semantic search can identify synonyms, related concepts, and contextual relevance–helping it better understand user intent, even when not explicitly stated.

Therefore, returning to the earlier example search query—“Impact of the 1918 New Zealand influenza pandemic”—a semantic search would likely return far more nuanced and relevant results. It would not only account for related phrasing such as “black flu”, but also surface content discussing economic consequences, social disruption, and public health responses related to the pandemic.


Is there still a place for keyword search?

There’s no doubt that semantic search offers a smarter, more intuitive way to navigate historical content—unlocking new opportunities to uncover hidden narratives, unexpected connections, and deeper insights from the past.

However, keyword search remains an essential tool, particularly in areas where precision is critical. It continues to play a vital role in:

  • Genealogy research where family history is traced through specific names, dates, and places—especially in resources like newspaper notices, obituaries, passenger lists, and electoral rolls.

  • Informing how certain terms appeared and evolved in mainstream conversation. For example, the word “quarantine” shows up across multiple pandemics, but its framing and public perception likely shifted dramatically between 1918 and 2020.

  • Remaining connected with outdated terminology. For example, the term “lunatic”, once commonly used in medical and legal documents related to mental health, is no longer considered appropriate today. Keyword search helps surface these historical references, providing valuable insight into how different conditions were historically understood and represented.

  • Identifying when ideas first emerged and changed. For example, when did the concept of “climate change” first appear in public records? Keyword search can help pinpoint its earliest mentions and trace how opinions and attitudes toward it have shifted across different time periods.


Where to from here?

As part of our beta testing of semantic search, we are also exploring a hybrid model that combines the best of both worlds—that is, the precision of keyword search with the contextual intelligence of semantic search. This allows users not only to find exactly what they’re looking for, but also to discover unexpected and relevant connections they might have otherwise missed.

As user expectations and research questions evolve, semantic search opens the door to a deeper, more intuitive understanding of history—one where context is just as important as content. Looking ahead, the next step is integrating AI-powered retrieval models like RAG (Retrieval-Augmented Generation), which unite contextual understanding with real-time referencing to further enrich discovery.

 

Veridian is actively investing in research and development around RAG, with the goal of starting to make this advanced technology accessible to our clients and their users this year. More updates will be shared soon.