News Sentiment Analyzer
Pricing
$6.50 / 1,000 article analyzeds
Go to Apify Store
News Sentiment Analyzer
Analyze news articles for sentiment using NLP. Extract positive, negative, and neutral signals from any news URL or keyword-based news feed.
News Sentiment Analyzer
Pricing
$6.50 / 1,000 article analyzeds
Analyze news articles for sentiment using NLP. Extract positive, negative, and neutral signals from any news URL or keyword-based news feed.
Search query — company name, ticker symbol, topic, or keyword phrase. Leave empty to use 'queries' array instead.
Run multiple queries in a single actor run. Each query gets its own sentiment summary. If both 'query' and 'queries' are provided, 'query' is prepended to the list.
Which news sources to scrape. Google News and Bing News provide the broadest coverage for most queries.
[ "google_news", "bing_news"]Maximum number of articles to scrape and analyze per query. Higher values give more data but take longer to run.
Language code for news results (ISO 639-1). Used to filter news to a specific language.
Country code for regional news results (ISO 3166-1 alpha-2). Affects which regional news appears in results.
How far back to look for articles. Shorter ranges give more current sentiment; longer ranges show trends.
Sentiment analysis model to use. 'afinn' is faster (word-level scoring). 'pattern' is slower but considers sentence structure.
Extract named entities (people, companies, locations) from articles and include per-entity sentiment scores.
Extract and cluster key topics and themes across articles. Useful for identifying what's driving sentiment.
Include the full extracted article text in each output item. Increases dataset size significantly — only enable if you need the raw text.
Minimum character length for an article to be analyzed. Articles shorter than this are saved to the dataset with a ARTICLE_TOO_SHORT error and no sentiment score.
Include a per-source sentiment breakdown in the run summary (stored in the Key-Value Store as OUTPUT).
Include a daily sentiment time-series in the run summary. Shows how sentiment is trending over time.