This tool measures the imaginative writing styles in a given English text, using a Machine Learning algorithm.
Texts which are more imaginative than a certain threshold are classified as Fiction and those below it are classified as Non-fiction. Please note that the algorithm does not check for factual information, and only analyses the writing style.
Raw Text
Upload file
Supported file formats : .pdf, .tex, .latex, .txt
Dashboard
Text type
Probability %
Word count
words
Average sentence length
:
File Statistics
POS Tags
NewsChase
NewsChase is an app which is based on the algorithm used in
Fictometer.
In this app the news article are analyzed based on their writing style as
some news article are written in such a way that it can manipulate the reader. And, such writing
style
is found to be similar to the ones used in fiction texts.
In the app, the news articles are assigned a score which shows the confidence score of the Machine
Learning algorithm.
It classifies the news articles in three categories, namely:
- Reliable : if the article is written in an informative style.
- Alright : if the article has moderate use of imaginative writing style.
- Beware : if the article may have manipulative content.
Examples
Here, is an example of three news articles written in a different style. Through the algorithm the articles are analyzed based on their writing style and are given three different tags with a confidence score of the algorithm :
- Reliable : if the article is written in an informative style.
- Alright : if the article has moderate use of imaginative writing style.
- Beware : if the article may have manipulative content.
- Headline : 'We are following Citizenship Bill Developments': US urges India to protect rights of religios minorities.
- Source : News18.com
- Category : Reliable
- Confidence : 100%
-
Ratios :
- Adverb/Adjective = 0.1428
- Adjective/Pronoun = 2.33
- Excerpt from article :
- Color Schemes Adverb, Pronoun, Adjective :
- Headline : Simbu goes on a pilgrimage to Sabarimala.
- Source : indiatoday.in
- Category : Beware
- Confidence : 99.98%
-
Ratios :
- Adverb/Adjective = 2.33
- Adjective/Pronoun = 0.25
- Excerpt from article :
- Color Schemes Adverb, Pronoun, Adjective :
- Headline : Simbu starts holy trip to Sabarimala after observing 40 day fast.
- Source : pinkvilla.com
- Category : Reliable
- Confidence : 100%
-
Ratios :
- Adverb/Adjective = 0.43
- Adjective/Pronoun = 1.76
- Excerpt from article :
- Color Schemes Adverb, Pronoun, Adjective :
Core Team
Contributing Students
Name | Institute | Period | |
---|---|---|---|
Arman Kazmi | IISER Bhopal | May - July 2019 | |
Anant Bhavsar | IIT Kharagpur | May - July 2019 | |
S. Koushik | IISER Bhopal | May - July 2019 | |
V Shivaraman | IISER Bhopal | May - July 2019 | |
Narendra Singh | Sitare University | June 2024 - |
About
In this work, we deploy a logistic regression classifier to ascertain whether a given document belongs to the fiction or non-fiction genre. For genre identification, previous work had proposed three classes of features, viz., low-level (character-level and token counts), high-level (lexical and syntactic information) and derived features (type-token ratio, average word length or average sentence length). Using the Recursive feature elimination with cross-validation (RFECV) algorithm, we perform feature selection experiments on an exhaustive set of nineteen features (belonging to all the classes mentioned above) extracted from Brown corpus text. As a result, two simple features viz., the ratio of the number of adverbs to adjectives and the number of adjectives to pronouns turn out to be the most significant. Subsequently, our classification experiments aimed towards genre identification of documents from the Brown and Baby BNC corpora demonstrate that the performance of a classifier containing just the two aforementioned features is at par with that of a classifier containing the exhaustive feature set.
A Simple
Approach to Classify Fictional and Non-Fictional Genres
M. R. Qureshi, S. Ranjan, Rajakrishnan P. R. and K. Shah, StoryNLP @ ACL 2019