> For the complete documentation index, see [llms.txt](https://help.researchgate.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.researchgate.net/community/understanding-how-we-show-you-recommendations.md). # Understanding how we show you recommendations At ResearchGate, it’s our mission to connect the world of science. At the same time, we recognize that every researcher has their own unique interests and goals. That's why we've designed our recommender system to show you the most relevant recommendations for *you*. ### **How we recommend content** Before we can show you content that we think you’ll be interested in, we first need to get an idea of what your interests are. For example, the **research you add to your profile** helps us understand your field of research, and show you similar research in your field. Sounds simple enough, right? Well, let’s say you’re researching electrostatics. An article on magnetostatics might be similar, but not *relevant*. Scientific disciplines contain sub-disciplines (or even sub-sub-disciplines). And even if an article is in your exact field, that doesn’t mean it’s relevant to your specific research. That’s why we use other signals to make more precise recommendations. Things like the **research you’ve read** on ResearchGate, the **people you follow**, and **your profile information** give us a clearer idea. To take it a step further, we use ‘**relevance ranking**’ to prioritize the *most relevant* content for you. While we use various signals to tailor your ResearchGate experience, we’re also committed to respecting your privacy. Our recommendations are based on limited data that we use to enhance your experience. ### **What makes a recommendation relevant?** A ‘signal’ is information that our recommender system uses to assess how relevant something is. The best signals for relevance are ones that come from you, such as **your profile details** and **your research**. The **people, research, and organizations you interact with** also help us predict the likelihood that you’ll find something interesting. Along with more general signals like **research similarity**, this information helps us recommend the right content for you. ### **How relevance ranking works** The signals we use help us find *potentially* relevant content to show you. To improve the chance that a recommendation is relevant, our algorithms take multiple signals into account when choosing what to show you. Generally, the research you’ve published or read plays the biggest role in deciding if a recommendation is relevant. In some cases, other signals might be more important. By alternating among different algorithms, we’re able to create a more dynamic experience while still focusing on your interests. In any case, the content that’s available to be recommended is ranked by these algorithms, allowing us to pick the best content for you. ### **Recommendations on ResearchGate** Across our platform and in notifications, we use recommendations to personalize your experience and help you discover research and people you might be interested in. Our recommender system is also used to show you relevant content like questions and discussions, job vacancies, journals, publishing opportunities, and sponsored content from organizations that partner with us. To help you find what you’re looking for, search results are also personalized based on signals such as your network and location. ### **How to keep your recommendations relevant** Here are some of the best ways to personalize your experience and get recommendations that are relevant to you: * **Keep your profile complete and up to date**. Updating your institution, skills and expertise, and other profile details helps us to show you content that matches your actual interests. * **Showcase your research contributions**. Creating publication pages for your research is a great way to create exposure for your work. It also helps us recommend research that’s similar to your own. * **Read research and interact with content that you’re interested in**. As you explore research on ResearchGate, we’ll suggest content related to your interests. * **Connect with researchers in your field.** Following colleagues, co-authors, and other experts is how you can keep up to date with their research and activity. Expanding or curating your network helps you get more—or more relevant—updates. ### **Next steps** We hope that learning about recommendations on ResearchGate has given you the tools to continue tailoring your experience to fit your research and interests. We’ll also continue to work on improving the relevance of the recommendations we show you. As we develop and refine these recommendations, we’ll continue to be transparent about how they work, what data we use, and how you can control what you see. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.researchgate.net/community/understanding-how-we-show-you-recommendations.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.