Autocomplete is a feature within Google Search that makes it faster to complete searches that you start to type. Our automated systems generate predictions that help people save time by allowing them to quickly complete the search they already intended to do.Where autocomplete predictions come from
Autocomplete predictions reflect real searches that have been done on Google. To determine what predictions to show, our systems look for common queries that match what someone starts to enter into the search box but also consider:
- The language of the query
- The location a query is coming from
- Trending interest in a query
- Your past searches
These factors allow autocomplete to show the most helpful predictions that are unique to a particular location or time, such as for breaking news events.
In addition to full search predictions, Autocomplete may also predict individual words and phrases that are based on both real searches as well as word patterns found across the web.
Autocomplete predictions aren’t perfect. There’s the potential for unexpected or shocking predictions to appear. Predictions aren't assertions of facts or opinions, but in some cases, they might be perceived as such. Occasionally, some predictions might be less likely to lead to reliable content. Here’s how we deal with issues like these.
First, autocomplete has systems designed to prevent potentially unhelpful and policy-violating predictions from appearing. These systems try to identify predictions that are violent, sexually explicit, hateful, disparaging, or dangerous, or which lead to such content. This includes predictions that are unlikely to return much reliable content, such as unconfirmed rumors after a news event.
Second, if the automated systems don’t catch problematic predictions, our enforcement teams remove those that violate our policies. In these cases, we remove the specific prediction in question and closely-related variations.
These systems help ensure that autocomplete doesn’t unintentionally shock or surprise people with predictions they might not expect. While they might prevent some predictions from appearing, autocomplete doesn’t prevent anyone from completely typing out a search query to get results, if they wish.
To help ensure autocomplete is a helpful experience for everyone, we have systems in place to prevent predictions that are in violation of Google Search’s overall policies or these policies for Search features:
- Dangerous content
- Harassing content
- Hateful content
- Sexually explicit content
- Terrorist content
- Violence and gore
- Vulgar language and profanity
Autocomplete also has these feature-specific policies:
- Elections-related predictions: We don't allow predictions that can be interpreted as:
- A position for or against any political figure or party, or
- A claim about the participation in or integrity of the electoral process.
- Health-related predictions: We don’t allow predictions about potentially medically hazardous health claims.
- Sensitive and disparaging terms associated with named individuals: We don’t allow predictions that associate potentially disparaging or sensitive terms with named individuals. This include predictions that:
- May be related to harassment, bullying, threats, inappropriate sexualization, or
- Expose private or sensitive information in a way that may cause harassment, identity theft or financial fraud.
We may make exceptions to these policies when the prediction has context related to artistic, educational, historical, documentary, or scientific content, or content that helps to further understanding and participation in current events and issues related to our society, politics, culture, and economy.
Difference between autocomplete & Google Trends
Autocomplete is a time-saving but complex feature. It doesn’t simply display the most common queries on a given topic. That’s why it differs from and shouldn’t be compared against Google Trends.
Google Trends is a tool for journalists and anyone else who wants to research the popularity of searches and search topics over time.