Smart Search – The New Default Search Experience in Web of Science
Smart Search is the new, default search experience in Web of Science, designed to be more intuitive and intelligent. Powered by semantic search and natural language processing, it allows users to enter queries in natural language and returns AI-ranked results for both documents and researchers.
As you begin typing, it offers helpful suggestions and understands your intent, whether you are using specific terms or long phrases. There's no need to master complex Boolean syntax, just type your query or keywords naturally and Smart Search constructs the Boolean query behind the scenes.
For users who prefer more control, Smart Search also supports traditional Boolean operators such as AND, OR, and NOT, enabling precise and flexible search refinement.
This enhanced experience makes discovering relevant research faster, easier, and more effective.
How Smart Search Works
When you enter a query in Smart Search, it goes through a multi-step process to deliver the most relevant results.
Query Analysis
Your input is first processed by our Natural Language Processing (NLP) parser, which understands the structure and context of your query. It identifies key entities such as author names, topics, and researcher IDs to ensure accurate targeting.
Query Construction
The parsed information is used to build a structured Web of Science (WOS) query, which is then sent to our search engine.
Dual Search Paths
Smart Search performs two types of searches:
Document Search: Semantic queries are converted into vector embeddings to interpret meaning and context. Boolean queries (using operators like AND, OR, and NOT) follow a standard keyword-based approach.
Researcher Search: Queries involving topics are enhanced with AI-based relevance ranking.
AI Ranking & Results Display
All results are ranked by AI to highlight the most relevant matches. Final results are presented in two tabs: DOCUMENTS and RESEARCHERS, making it easy to explore both types of content
Smart Search features
One-Box Search is designed for simplicity, just type naturally into a single search field without needing to select specific fields or use multiple boxes. It’s not conversational, but it intelligently interprets your input across multiple fields.
It handles typos, supports multilingual recognition, and automatically converts natural language into structured Boolean queries. For example, a query like “How does climate change impact global warming?” is expanded to search across both topic fields and all fields using Boolean logic.
For users who prefer more control, One-Box supports Boolean operators like AND, OR, and NOT, as well as parentheses for advanced query refinement.
You can choose to search either:
All Databases: One-Box searches all fields across all databases in one go, offering a seamless and comprehensive experience. Individual databases cannot be searched separately.
Web of Science Core Collection (WoSCC): One-Box offers the flexibility to search all fields exclusively within WoSCC.
Results are displayed in two tabs: DOCUMENTS and RESEARCHERS, making it easy to explore both types of searches.
Understanding user search query/input (Even If You Use ‘AND’ or ‘OR’ or 'NOT')
Examples:
| What You Type | How the System Interprets It | Boolean Query It Actually Runs |
| DNA AND RNA | Boolean Search | ((TS = DNA) AND (TS = RNA)) |
| AI OR machine learning in medicine | Boolean Search | ((TS = AI) OR (TS = machine learning in medicine)) |
| cancer NOT chemotherapy | Boolean Search | (TS = cancer) NOT ((TS = chemotherapy)) |
One-Box Search vs. Advanced Search
Advanced Search maintains the existing search functionalities for experienced users who prefer precise search or complex Boolean queries.
| Feature | Smart Search | Advanced Search |
| Search functionality | One-Box search (new) |
All existing search features: Fielded Search (same as Document Search) Query Builder (same Advanced Search) Citated reference search Structured search
|
| Ease of use | Simple, intuitive, user type in natural language. | Precise (Query Builder), requires Boolean syntax (AND, OR, NOT) knowledge |
| Typeaheads & Autocomplete | AI-enabled typeaheads | AI-enabled typeaheads not supported |
|
Autocorrection (showing results ‘for’ instead ‘of’)
Did you mean? |
Yes, both supported
|
Autocorrection not supported Did you mean? supported
|
| Boolean Query Conversion | Automatic for natural language queries. | Manual (user customize query) |
| Boolean Search result | Summary page, document tab. Preferred search results can be selected | Summary page |
| Semantic search result | Supported | Semantic search not supported |
| Search personalization | Supported | No |
| Translated Search | Supports UI languages: Simplified Chinese, Traditional Chinese Japanese, Korean, Portuguese Russian, Arab, Spanish |
No |
Multilingual Search
One-Box Search supports up to 8 languages, allowing users to enter queries in their preferred language. When a supported language is detected, a language toggle appears on the search results page, enabling users to switch between English and their chosen language effortlessly.
- On the results page, all 50 titles are automatically translated into the selected language.
- Abstracts remain in English unless the user clicks the Translate button on an individual article card.
- On the full record page, both the title and abstract are translated automatically but only if the user chooses to translate the abstract.
This makes the search experience truly multilingual, helping users explore research in the language they’re most comfortable with.
Autocorrection feature (Handling Typos & Misspellings)
Even if you type something incorrectly, the system helps by:
- Autocorrecting mistakes if not results (showing results for ‘Animale’ instead of ‘Animal’).
- For misspelt words e.g. Dogg, it will show results and ask “Did you mean?” ‘Dog’ on summary page if input is unclear.
Example:
You type Physic → It will return results for "Physics"
You type Crispr gene editng → It suggests "Did you mean? Crispr gene editing on results page
Personalized, Context-Aware Typeaheads
Intelligent typeahead help speeds up searches by predicting what user need, reduces effort by personalizing suggestions based on your previous searches for signed-in users and helps discover related research by suggesting relevant topics.
As users start typing, intelligent typeaheads provide suggestions based on:
- Popular Searches - Takes Web of Science history into consideration and when users sign in, the experience becomes even more personalized and context-aware
- Topics – Suggests topics relating to user query
- Author Names – Matches authors in Last Name, First Name format
- Affiliations – Suggests universities, institutions and research organizations.
- Journal Names – Suggests known journals as you type.
If you often search for "machine learning," you might see suggestions like "Machine Learning in Healthcare" or "Deep Learning Models." If you type "Smith, J," the system may prioritize "Smith, John (MIT)" based on your history.
Dual-Tab Interface – Search results
When you search using One-Box, results are neatly displayed on two separate tabs:
Documents Tab: Display document search results.
Researchers Tab: Display researchers, number of documents published, affiliation etc. and users can view their profiles.
| User Query | Document Tab (Search results) | Researcher Tab (Search results) |
| Author name(s) | Search results: document(s) published by the author |
Search results: authors that match the name (unclaimed and claimed)
|
| Topic |
Search results: document(s) on that topic (covid)
|
Search results: authors who write on that topic based on number of publication and citations. |
| Institution, Affiliation |
Search results: document(s) written by the address listed on the paper
|
Search results: authors who currently work at that institution or who have worked at institution
|
| Journal/Publication title |
Search results: publication(s) published in that journal
|
Search results: authors have published in that journal
|
| Article title |
Search results: document(s) that match the title
|
Search results: author(s) who wrote that publication(s)
|
| Author identifier |
Search results: document(s) written by that author(s) that match the identifier
|
Search results: author(s) that match the identifier
|
| Document identifier |
Search results: exact document specified
|
Search results: Authors that wrote the article
|
| Multiple fields (Author name and pub year; Author name affiliation or topic) |
Results come back with document(s) published by the author and affiliation (address listed) or topic
|
Search results: author profiles that match the name
|
Document Tab (search results): Users can select preferred search results; combined Boolean and semantic, semantic only and Boolean only.
Combined Boolean and Semantic Search Results: Once user search is processed, we combine two approaches:
- Boolean search provides precision.
- Semantic search brings context-aware flexibility.
The system ranks and blends results for the most relevant search results.
Example Hybrid Search Results for:
User query: Impact of global warming on food security
Search results return both Boolean and Semantic search results e.g.
1️) Paper titled " Food Security: The Challenge of Feeding 9 Billion People" (Boolean match).
2️) Paper titled “The Role of Digital Agriculture in Mitigating Climate Change and Ensuring Food Security: An Overview” (Semantic match).
The ranking algorithm blends both sets of results, presenting you with the most relevant documents and researcher profiles on separate tabs.
Researcher Tab (search results)
Author name search: In the researcher tab, we are replicating the functionalities of the Advanced Search page's Researcher Search. For name searches, use the format "Last name, First name" or select a suggestion from the one-box. If you enter "First name, Last name," it will be treated as a 'topic' rather than an 'author name' due to system constraints.
Author Topic Search: For searches specifically related to an author topic, we leverage the topic model to return top 100 authors relevant to that topic based on number of documents published and citation count.
For all other entity-based searches, the system returns authors based on their publications (e.g., those who have published in a particular journal or are affiliated with a specific institution).
Example:
User enter search term/query “AI ethics.”
We will not only return documents on AI ethics in the document tab but in a separate tab, displays a list of leading researchers (top 100 authors) working on AI ethics, not ranked but authors most publications and citations on AI ethics. For other types of searches, you we display authors associated with the relevant journals or institutions or user query.