TEXT CLASSIFICATION + PROXIMITY
Budget: $30 – $250 AUD
Python Code.
We will be working with very very long documents, and want short summaries.
1. Enter text.
2. Enter keyword. This keyword is what the code analysis should centre around. For example if summarising the book Moby Dick, and the keyword was WHALE, we would want summaries regarding every reference to the whale.
2. Classify text to extract meaning/summarise. Only summarise/classify text close to keyword, i.e. in the example above WHALE.
3. Also extract and place into a report/document all:
- Sentences that mention keywords.
- Paragraphs that mention keywords.
We may need to select a proximity (number of words) to search around each keyword, or use full stops/paragraph breaks to determine which text to include/exclude in classification.
We will be working with very very long documents, and want short summaries.
1. Enter text.
2. Enter keyword. This keyword is what the code analysis should centre around. For example if summarising the book Moby Dick, and the keyword was WHALE, we would want summaries regarding every reference to the whale.
2. Classify text to extract meaning/summarise. Only summarise/classify text close to keyword, i.e. in the example above WHALE.
3. Also extract and place into a report/document all:
- Sentences that mention keywords.
- Paragraphs that mention keywords.
We may need to select a proximity (number of words) to search around each keyword, or use full stops/paragraph breaks to determine which text to include/exclude in classification.