The Mona Lisa is the most famous painting in the world. Most people know who she is and generally what she looks like.
If you asked 10 people to describe her, while they’ll all arrive at similar shapes and phrases, they’ll use different words to describe the same painting.
Even if you asked 10 people to describe what the Mona Lisa is, they might use different words like: artwork, painting, or masterpiece.
This is called synonymy. And if you’re using traditional keyword search to analyze text, synonymy is a problem.
How traditional keyword search works
Traditional keyword search is a type of information retrieval method where a search engine or database looks for exact matches of the keywords or phrases input by the user. Here's a simple breakdown of how it works:
Indexing: The search engine first "indexes" all the documents (web pages, articles, etc.) in its database. This involves scanning all documents and creating a list of words or terms that appear in them.
Querying: When a user inputs a search term or keyword, the search engine looks for an exact match of these terms in its index.
Ranking: The search engine then ranks the search results based on their relevance, which is typically determined by how many times the search term appears in the document, whether it appears in the title or headers, its proximity to other search terms, among other factors.
Returning results: Finally, the search engine returns the ranked list of search results to the user.
Traditional keyword search can be very effective for finding documents that contain specific words or phrases. However, it also has significant limitations, and synonymy is one of them.
The problem arises because traditional keyword search engines are not good at understanding the semantics or meaning behind words. They look for exact matches of search terms and do not understand that different words can have the same or similar meanings.
For example, if a user searches for "automobile," a traditional search engine would not return documents that only contain the word "car," even though "car" and "automobile" are synonyms and essentially mean the same thing. This means the search engine could miss out on relevant documents simply because they use different words for the same concept.
This issue becomes even more problematic when dealing with highly contextual or domain-specific languages, like customer feedback, and different terms might be used to describe the same concept.
Semantic search is the solution
In previous posts we talked about contextual text embeddings and their benefits. One of the major implications of turning text into text embeddings is to conduct semantic search (like we do at CustomerIQ).
Semantic search is an approach to locating information that uses embeddings to understand the searcher's intent and the contextual meaning of the search query in order to provide more relevant results.
Unlike traditional keyword search, which looks for exact matches of search terms in the content, semantic search considers the context, synonyms, intent, and even the tone of the query to find the best match.
A few key features of semantic search
- Query Understanding: Semantic search systems aim to understand the intent behind the query, not just the keywords. For example, if someone searches for "apple," the system tries to determine whether the user is interested in the fruit, the tech company, or something else entirely.
- Context Awareness: Semantic search also considers the context in which words are used. The meaning of a word can change depending on its context, and semantic search systems aim to understand this. For example, in the sentence "I need a mouse for my computer," the word "mouse" has a different meaning than in "I saw a mouse."
- Use of Synonyms: As we have been discussing, semantic search acknowledges synonymy. If a user searches for "car," a semantic search engine can also return results related to "automobile," "vehicle," "motorcar," etc.
Semantic search provides a more sophisticated, nuanced, and relevant set of search results compared to traditional keyword search.
What this means for customer feedback analysis
Just as 10 people use different words to describe Mona Lisa, your customers are going to use different words to describe your features, benefits, and jobs you help them do.
By using semantic search to search across your database of customer insights we can accomplish a number of things we couldn’t accomplish with traditional keyword search:
- Improved relevance: By understanding the context and meaning behind words and phrases, semantic search can provide more relevant results. It can better understand synonyms, related terms, and even the underlying intent of the query, leading to more accurate search results. This is especially important in analyzing customer feedback because users and customers rarely use the same words to describe a feature or issue that your team would. Semantic search helps us to surface relevant insights much better.
- Handling complex queries: Traditional keyword-based search can struggle with complex or ambiguous queries like a long question or maybe just a “thought.” Semantic search, on the other hand, can understand the meaning behind these queries and provide better results, even when the query uses different words than the target text.
- Natural language queries: Semantic search can handle natural language queries, allowing users to search using conversational language instead of forcing them to think in terms of keywords. This makes the search process more intuitive and user-friendly.
- Cross-lingual search: Embeddings can be created for different languages, enabling semantic search across multiple languages. This allows users to find relevant content in other languages, even if they don't know the exact translation of their query.
- Personalized search: By understanding the context and meaning of the content, semantic search can help deliver personalized search results based on users' preferences, interests, and browsing history.
Overall, semantic search using embeddings has the potential to revolutionize how we search and retrieve information, making the process more intuitive, accurate, and efficient. It can provide a more natural way to interact with the textual data we collect, leading to a better user experience and more relevant search results.
How CustomerIQ leverages semantic search to create customer research magic
As we’ve mentioned, when qualitative data is stored in CustomerIQ folders, we extract the insights and turn them into text embeddings. This helps us perform an array of game-changing analyses including semantic search.
How to use Semantic search in CustomerIQ
Within the action bar on any view you’ll see a search field called “Topic search.” You can use this field to filter all the insights in view by topic. If you know what you’re looking for, write it explicitly. If you don’t, pose a simple question. CustomerIQ’s topic search will return the most relevant insights in order.
Examples
Using CustomerIQ’s topic search can help you uncover themes, identify trends, and address specific issues more effectively. Here are some examples of how semantic search can be employed in this context:
- Identifying common issues: You can use semantic search to find feedback related to specific problems or challenges, even if customers use different words or phrases to describe them. For instance, searching for "the app is slow" could also retrieve feedback that mentions "app takes too long to load" or "frustrated staring at a blanks screen"
- Analyzing sentiment: Semantic search can help you find feedback with specific sentiments, such as positive, negative, or neutral. For example, you could search for "happy customers" or "dissatisfied users" to identify feedback that matches those sentiments.
- Discovering feature requests: You can use semantic search to identify customer requests or suggestions for new features, improvements, or enhancements. A query like "feature requests" or "suggested improvements" could help you find relevant feedback.
- Grouping related feedback: Semantic search can cluster similar feedback together, making it easier to analyze and address common themes. For example, you might search for "payment issues" and discover feedback related to declined cards, confusing payment options, or slow processing times.
- Understanding context: You can use semantic search to explore feedback in a specific context, such as a recent product update, a marketing campaign, or a customer service interaction. Queries like "feedback on new update" or "responses to email campaign" can help you find relevant insights.
- Comparing products or services: Semantic search can help you compare feedback on different products, services, or features by understanding the context and meaning behind the comments. For instance, you might search for "Product A vs Product B" to find customer opinions comparing the two.
- Cross-lingual analysis: If your customer feedback database contains entries in multiple languages, semantic search can help you analyze and compare feedback across languages, even if you don't know the exact translations of your search terms.
Try out semantic search today free
At CustomerIQ, semantic search is a big part of how we help teams build and market products people love. In minutes you can setup a database of customer insights for you to search and discover new themes to guide your roadmap and messaging.
