NLP with Aylien

100%

NLP with Aylien

✓ Published0🌍 Public

Last edited Oct 10, 2019

Created on Oct 10, 2019

This example demonstrates sentiment analysis by sending a sample text to the Aylien Text API, which returns hashtags summarizing the text’s tone and topics. The code constructs an HTTP request using XQuery’s `http:send-request` and the `fn:encode-for-uri` function, targeting the API’s `/hashtags` endpoint with a fixed string about a skeptical reaction to a plan. The result, formatted as XML, would display the generated hashtags but does not visualize them; instead, it focuses on the API interaction itself, relying solely on the Aylien service without any graphical rendering or charting library.

AI-generated description

Similar vizzes

Loading thumbnail…

Text Mining at Scale (XQuery Working Group) Natural Language Processing

This example demonstrates how to analyze a corpus of genuine and fake news articles using XQuery and the Aylien Natural Language Processing API. It shows how to create a database of cleaned article records, list and rank news sources by veracity, and perform text analysis services such as sentiment classification, entity extraction, and automatic summarization. The code relies on XQuery 3.1 functions for data processing and HTTP requests to communicate with Aylien’s TextAPI.

CCliffordAnderson

72% match

Loading thumbnail…

HTTPie post to alchemy entity extraction API

This example demonstrates how to call the AlchemyAPI entity extraction service from the command line using HTTPie, sending a URL for named-entity recognition. The command posts to `URLGetRankedRankedNamedEntities` with an API key and the target text file, returning ranked entities as JSON. It highlights the simplicity of HTTPie’s `--form` flag for URL-encoded POST data, contrasting with heavier client libraries. The visualization context is implicit: the response would typically feed a charting library like D3 or a force-directed graph, but the code shown only performs the API request. No rendering or data processing is visible beyond the raw HTTP call.

CCliffordAnderson

59% match

Loading thumbnail…

A little playful XQuery

This playful XQuery example transforms a user’s phrase by replacing each word with a random antonym fetched from the Oxford Dictionaries API. It demonstrates a game-like text manipulation, showing the original sentiment inverted. The code uses XQuery 3.1, the `http:send-request` and `random:integer` functions, and the MarkLogic HTTP client to query the Oxford entry endpoint. For each word, it retrieves antonym sets, picks one randomly, and falls back to the original word when no antonym exists.

CCliffordAnderson

56% match

Loading thumbnail…

For XQuery4Humanists

This example visualizes the frequency and distribution of words extracted from a TEI-encoded poem, processing the text to remove punctuation, normalize case, and tokenize it into a list. The visualization shows the resulting word list as a simple textual display, highlighting the raw output of the XQuery processing pipeline. The code uses XQuery 3.0 functions like `fn:tokenize`, `fn:lower-case`, and `fn:replace` to clean the data, pulling the source directly from a remote XML file hosted on GitHub. The rendering relies solely on the XQuery return, with no additional JavaScript or charting libraries involved.

CCliffordAnderson

55% match

Loading thumbnail…

Sentiment

This example visualizes sentiment analysis by rendering a simple HTML page that loads the `sentimental` library from unpkg.com. The visualization draws on sentiment data processed through the `sentimental` API, which evaluates text and outputs a sentiment score. The page uses a minimal setup with CSS and JavaScript, where the main application logic resides in a bundled `bundle.js` file. The React framework is referenced, and the prototype connects sentiment analysis results to a visual representation, though the concrete rendering method is not detailed beyond relying on `sentimental` for the analysis.

Llars-ruijs

55% match

Loading thumbnail…

Extracts entities with geographic attributes using the Alchemy api

This example shows geographic entities extracted from a web-accessible text, filtered to include only those with associated geo-coordinates. The XQuery script sends a POST request to the Alchemy API’s URLGetRankedNamedEntities endpoint, supplying an API key and a target URL, then parses the returned XML to select entities that contain a `<geo>` element. The visualization relies on the Alchemy API for entity extraction and geographic tagging, while the code itself handles the HTTP request and response processing without additional rendering libraries. The data source is a plain-text file hosted on GitHub, and the output is a list of entities with location data.

CCliffordAnderson

55% match

Loading thumbnail…

Alchemy Named Entity example for class

This example demonstrates how to extract named entities from user-supplied text and visualize them as an interactive force-directed graph, where each entity is a node sized by its relevance score. It employs the AlchemyAPI via an `httpclient:post()` call to `TextGetRankedNamedEntities` for entity extraction, then uses the `d3.forceSimulation` layout to position nodes by mutual relations. The graph is rendered using D3.js SVG paths, with entity labels and connection lines drawn from the JSON response, and the radial node styling relies on D3’s built-in scales. The code also references an external CSS file for styling but leaves the graph and interaction logic entirely in JavaScript.

CCliffordAnderson

54% match

Loading thumbnail…

Looking up words in the OED with XQuery

This example demonstrates a playful text-rewriting process where each word in a sentence is replaced by a synonym retrieved from the Oxford Dictionaries API. It begins by sending two HTTP requests to the Oxford Dictionaries API endpoints for word definitions and synonyms, then defines a custom XQuery function that isolates the first synonym for a given word. The main logic tokenizes the input sentence and applies this synonym-lookup function iteratively, finally rejoining the substituted words into a new sentence. The visualization relies on XQuery’s HTTP client capabilities for API interaction and string manipulation functions to process the text, with no graphical rendering involved.

CCliffordAnderson

54% match