What is Detect Dialect?

Detect Dialect is a unique search tool for colloquial Arabic content on Twitter. Replacing the general "Arabic" search option with a dialect-specific search, Detect Dialect offers users targeted access to the true voice of the man on the street.

What are Arabic dialects?

Two varieties of the language exist side by side throughout the Arabic speaking world. One is the standard variety, also known as Modern Standard Arabic or literary Arabic, which is learned by Arabic speakers through formal education and is uniform throughout the entire Arabic speaking world. This variety of the language is used for most formal communications. For all regular daily communications, Arabic speakers use their local dialect, commonly known as spoken or colloquial Arabic, which they acquire naturally as their mother tongue. There are numerous such dialects, sometimes differing even between two neighboring towns, but they can generally be classified into five main groups: Maghrebi, Egyptian, Levantine, Gulf, and Iraqi.

A common misconception is that all written communication in Arabic is conducted through the uniform, standard variety. While this is not necessarily the case even in literature and media, it is certainly not the case in social media platforms, where many Arabs write in their local "spoken" dialect.

Why focus on dialects?

Searching a certain Arabic dialect allows users to -

• Focus the search: The "Arabic" search option currently found in all search engines brings together results from more than 20 Arabic speaking countries, with no effective way to narrow the search to a specific Arabic speaking nation. Detect Dialect enables users to focus their research on the people that really interest them -- whether they are Egyptians, Tunisians, Syrians, Saudis or Iraqis – and identify trends at a finer level.
• Get access to original content: As opposed to tweets in standard Arabic, which are often no more than retweets of the same mainstream media story, Detect Dialect gives users direct access to original, personal content composed by Arabic speakers in their mother tongues, thus best representing the true voice of the people.