Uploaded image for project: 'Stanbol'
  1. Stanbol
  2. STANBOL-760

Sentiment Summarization EnhancementEngine

    Details

    • Type: New Feature
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 0.12.0
    • Component/s: Enhancer
    • Labels:
      None

      Description

      An EnhancementEngine that consumes word level Sentiment annotations and sums them up to

      • Noun Phrases
      • Sentences
      • the whole Document

      Notes:

      • As this EnhancementEngine is expected to create Enhancement we will need to define how SentimentAnnotation should be represented by using the Stanbol enhancement Structure.
      • This Engine should also support the detection of negations (e.g. this was not a nice trip, the weather was not as bad as the forecast suggested)

        Issue Links

          Activity

          Hide
          rwesten Rupert Westenthaler added a comment -

          Note: this comment is intended to be added to the documentation of the Stanbol Enhancement Structure

          How to represent Sentiments in the Stanbol Enhancement Structure:

          1. we need to decide if we want to create an new Annotation type (SentimentAnnotation) or if we use normal TextAnnotation with some additional Properties representing the Sentiment.

          2. we need to decide how we represent Sentiment. A simple representation could include "∑ positive sentiment tags", "∑ negative sentiment tags" and "∑ positive - negative sentiment tags" over a Section - NounPhrase, Sentence, the whole text. A more extensive description could also include/link to the NIF representation of the annotated section AND the Words with sentiment annotations (see STANBOL-741 for more info on NIF).

          As this EnhancementEngine also requires to select longer sections of the Text it would also benefit from the changes to fise:TextAnnotations already suggested on [1]

          Quote:

          > NOTE: In future version TextAnnotations might switch to a Model that uses
          >
          > * fise:selection-prefix: some words/characters before the selected section.
          > * fise:selection-head: the first few word/characters of a the selected section within the text. Alternative to fise:selected-text in case bigger sections of the parsed content need to be selected.
          > * fise:selection-tail: the last few words/characters of a selected section. To be used together with fise:selection-head.
          > * fise:selection-suffix: some words/characters after the selected section.

          [1] http://stanbol.apache.org/docs/trunk/components/enhancer/enhancementstructure.html#fisetextannotation

          Show
          rwesten Rupert Westenthaler added a comment - Note: this comment is intended to be added to the documentation of the Stanbol Enhancement Structure How to represent Sentiments in the Stanbol Enhancement Structure: 1. we need to decide if we want to create an new Annotation type (SentimentAnnotation) or if we use normal TextAnnotation with some additional Properties representing the Sentiment. 2. we need to decide how we represent Sentiment. A simple representation could include "∑ positive sentiment tags", "∑ negative sentiment tags" and "∑ positive - negative sentiment tags" over a Section - NounPhrase, Sentence, the whole text. A more extensive description could also include/link to the NIF representation of the annotated section AND the Words with sentiment annotations (see STANBOL-741 for more info on NIF). As this EnhancementEngine also requires to select longer sections of the Text it would also benefit from the changes to fise:TextAnnotations already suggested on [1] Quote: > NOTE: In future version TextAnnotations might switch to a Model that uses > > * fise:selection-prefix: some words/characters before the selected section. > * fise:selection-head: the first few word/characters of a the selected section within the text. Alternative to fise:selected-text in case bigger sections of the parsed content need to be selected. > * fise:selection-tail: the last few words/characters of a selected section. To be used together with fise:selection-head. > * fise:selection-suffix: some words/characters after the selected section. [1] http://stanbol.apache.org/docs/trunk/components/enhancer/enhancementstructure.html#fisetextannotation
          Hide
          rwesten Rupert Westenthaler added a comment -
          Show
          rwesten Rupert Westenthaler added a comment - resolved with http://svn.apache.org/r1533422

            People

            • Assignee:
              rwesten Rupert Westenthaler
              Reporter:
              rwesten Rupert Westenthaler
            • Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved:

                Development