I really like the concept of this app! Could you explain how the app determines whether a news article is good or bad? What kind of algorithms do you use?
The app uses algorithms of sentiment analysis https://en.wikipedia.org/wiki/Sentiment_analysis All news classify by their positive/negative features. A lot of news sources for different languages were analyzed to automatically extract the typical "good" or "bad" patterns for classification.
Summarizer’s unique feature is the possibility to create different kinds of summaries:
Theme-oriented: the output summary includes the sentences, which are mostly relevant to a given topic (e.g. politics, economics, sports and etc.);
Structure-oriented: the summary content depends on input document structure (e.g. scientific article, patent, news article);
Concept-oriented: the importance of sentences is determined with respect to a number of user defined concepts.
Try all of this features to create your appropriate summary.
Intellexer Summarizer combines different natural language processing algorithms in order to obtain the highest results. We use hybrid approach to text information analysis which is based on using not only linguistic and statistical information, but also a set of complex semantic rules developed by linguists. Taking into consideration the knowledge of facts and deep semantic relations between them, summarization rules assign a certain value per sentence of the original text. This value defines the importance of the sentence in respect to the idea of the text.
