Yeroniomus
Joined 10 years ago
Karma
47
Submissions
43
Member since
Sep 15
Recent submissions
Comment · 9 years ago
Thanks a lot for the suggestions and feedbacks to everyone.
My nearest plans: small interface redesign, improvement of sentiment analysis algorithm, personalization of news feeds and the iOS launch. Keep on updates!
Comment · 9 years ago
Yes, not very good screenshot for the landing page. But all of the predictions were made by AI :-)
Comment · 9 years ago
Not now. It does a general prediction. Maybe I will add this feature in future releases.
Comment · 9 years ago
After collection of possible positive/negative features with weights I used logistic regression classifier with some modifications (e.g. position algorithm) to classify the article. It determines the article polarity based on features (words, phrases and etc.)
Comment · 9 years ago
Thanks a lot for the link. I've used the technology called Paragraph Vectors https://cs.stanford.edu/~quocle/paragraph_vector.pdf for sentiment features extraction. Training collections were created in a semi-automatic mode and included news title+short description gathered from popular RSS feeds.
Comment · 9 years ago
Hello, Hacker News users! It's my first Android app and first experience of Android development :-).
SentiNews is based on sentiment analysis which helps to classify news as positive or negative. What do you think about general concept of the app? Will be waiting for your feedback.
Comment · 9 years ago
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.
Comment · 9 years ago
Thanks a lot for your recommendations about the UI and the app in general. I'll update it in a near future. It's my first Android project ("just for fun") and I hope you will use SentiNews from time to time.
> Very little content, only like 5 articles from each newspaper. All news are mostly political.
You can swipe beetwen pages and see different news topics (not only politic news). SentiNews includes a lot of categories (Sport, Technology, Science and etc.) from the most popular news sources.