Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,8 @@ serve:
clean:
rm -rf site .env

check: lint

lint:
docker run --rm -v "$$(pwd):/workdir" davidanson/markdownlint-cli2:latest

Expand Down
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
2 changes: 1 addition & 1 deletion docs/de/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ Der „News Deframer“ ist ein sprachliches Analysetool für Ihre bevorzugten N

* Wir [ersetzen](showcases/index.md) die Portalseite.
* Jede Schlagzeile wird in neutrale Sprache überführt (Reduktion von Clickbait, Reizüberflutung, Suggestion und Framing).
* Integrierte [Trendanalyse](trends/index.md) zur Erkennung von Talking Points.
* Integrierte [Trendanalyse](trends/index.md) zur Erkennung von Talking Points und [Sentiments](sentiments/index.md) Visualisierung.
* Vergleich verschiedener Nachrichtenportale, z. B. "Tagesschau" mit "Apollo News" oder "Bild" mit dem "Bayerischen Rundfunk".
* Per Klick gelangen Sie zurück zum Originalartikel bzw. zur ursprünglichen Portalseite.

Expand Down
2 changes: 2 additions & 0 deletions docs/de/links.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@
- [Quellcode](https://github.com/deframer/news-deframer/)
- [Quellcode Trend Mining](https://github.com/deframer/news-deframer-mining/)
- [Fehler melden](https://github.com/deframer/news-deframer/issues)
- [MEmoLon – The Multilingual Emotion Lexicon](https://github.com/JULIELab/MEmoLon)
- [Parquet Dateien für MEmoLon](https://github.com/deframer/memolon-parquet/)
- [Lizenz](license.md)

## Kontakt
Expand Down
3 changes: 3 additions & 0 deletions docs/de/mobile-app/index.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
# Mobile App

Demnächst verfügbar.
12 changes: 12 additions & 0 deletions docs/de/sentiments/index.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
# Sentiments

<img src="/assets/screenshots/portal/apollo-news_sentiments.png" alt="Apollo News - Sentiments" width="1000"/>

* **Sentiments**: Zeigt die emotionalen Werte der ausgewählten Artikel basierend auf lexikalischen Schätzungen.
* **Original vs. Deframed**: Wechseln Sie zwischen den ursprünglichen Artikeltexten aus dem RSS-Feed und den deframten Versionen, um die vom News Deframer entfernte emotionale Wirkung zu visualisieren.

## Warum Sentiments?

Wir verwenden einen VAD/VAC (Dimensional) und BE5 (Diskret) Ansatz zur Erkennung von Stimmungen und Emotionen in Texten. Dabei nutzen wir die Sentiment-Werte von [MEmoLon](https://github.com/JULIELab/MEmoLon), einem Emotionslexikon für über 90 Sprachen. Das **VAD**-Modell (Valenz, Arousal/Erregung, Dominanz) bewertet die allgemeine Stimmung auf einer Skala von 1-9 in den Bereichen Valenz (Polarität/Angenehmheit), Arousal (Aktivierung/Erregung) und Dominanz (wahrgenommene Kontrolle). Das **BE5**-Modell misst die Intensität der diskreten Emotionen – Freude, Wut, Traurigkeit, Angst und Ekel – auf einer Skala von 1-5.

Es gibt grundlegende wissenschaftliche Erkenntnisse, die diese Methodik stützen: fMRT-Experimente zeigen, dass das Lesen bestimmter Wörter tatsächlich messbare emotionale Reaktionen im Gehirn hervorrufen kann. Weitere Details zu dieser Theorie finden Sie in dieser [Dissertation](https://edoc.ub.uni-muenchen.de/18933/1/Danner_Sandro_C.pdf).
2 changes: 1 addition & 1 deletion docs/en/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ News Deframer analyzes journalistic neutrality and framing in news articles. By

- We [replace](showcases/index.md) the portal page.
- Every headline is reformulated in neutral language (reducing clickbait, overstimulation, persuasion, and framing).
- Built-in [trend analysis](trends/index.md) for detecting recurring talking points.
- Built-in [trend analysis](trends/index.md) for detecting recurring talking points and [sentiments](sentiments/index.md) visualization.
- Comparison of major news outlets, e.g., "The New York Times" and the "New York Post" or CNN and Fox News.
- One click restores the original article or the original portal page.

Expand Down
2 changes: 2 additions & 0 deletions docs/en/links.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@
- [Source Code](https://github.com/deframer/news-deframer/)
- [Source Code Trend Mining](https://github.com/deframer/news-deframer-mining/)
- [Bug Report](https://github.com/deframer/news-deframer/issues)
- [MEmoLon – The Multilingual Emotion Lexicon](https://github.com/JULIELab/MEmoLon)
- [Parquet files for MEmoLon](https://github.com/deframer/memolon-parquet/)
- [License](license.md)

## Contact
Expand Down
3 changes: 3 additions & 0 deletions docs/en/mobile-app/index.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
# Mobile Application

Coming soon.
12 changes: 12 additions & 0 deletions docs/en/sentiments/index.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
# Sentiments

<img src="/assets/screenshots/portal/nypost_sentiments.png" alt="New York Post - Sentiments" width="1000"/>

- **Sentiments**: Displays the emotional scores of the selected articles based on lexical estimates.
- **Original vs Deframed**: Toggle between original texts from the RSS feed and their deframed counterparts to visualize the emotional impact removed by News Deframer.

## Why Sentiments?

We use a VAD/VAC (Dimensional) and BE5 (Discrete) approach to detect sentiments and emotions in texts, leveraging sentiment scores from [MEmoLon](https://github.com/JULIELab/MEmoLon), an emotion lexicon for 90+ languages. The **VAD** (Valence, Arousal, Dominance) model evaluates overall mood on a 1-9 scale across Valence (polarity/pleasantness), Arousal (activation/excitement), and Dominance (perceived control). The **BE5** model measures the intensity of discrete emotions—Joy, Anger, Sadness, Fear, and Disgust—on a 1-5 scale.

There is fundamental science supporting this methodology: fMRT experiments demonstrate that reading specific words can indeed induce measurable emotional responses in the brain. For more details on this theory, refer to this [PhD thesis](https://edoc.ub.uni-muenchen.de/18933/1/Danner_Sandro_C.pdf).
4 changes: 4 additions & 0 deletions mkdocs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,8 @@ plugins:
- News Deframer: index.md
- Showcases: showcases/index.md
- Trends: trends/index.md
- Sentiments: sentiments/index.md
- Mobile App: mobile-app/index.md
- Status: todo.md
- RSS Proxy: rss-feed.md
- Sponsors: sponsors.md
Expand All @@ -59,6 +61,8 @@ plugins:
- News Deframer: index.md
- Showcases: showcases/index.md
- Trends: trends/index.md
- Sentiments: sentiments/index.md
- Mobile App: mobile-app/index.md
- Status: todo.md
- RSS Proxy: rss-feed.md
- Sponsoren: sponsors.md
Expand Down
Loading