Tentative Insights into the Somali Language Usage from Google Searches

Tentative Insights into the Somali Language Usage from Google Searches

Abstract

Collapse of the state in 1991 affected the use of the Somali language for print media due to the destruction of the state printing agency in Mogadishu at which newspapers and books were printed. Digital media has filled the vacuum and proved a fertile ground for research into the Somali language usage.

Based on Google searches of Somali words, phrases and sentences with an emphasis on Somali spelling rules and commonly confused Somali words and phrases, this paper takes advantage of the unstructured but continually updated corpus of the World Wide Web to make tentative conclusions from examples discussed in it.

The paper raises questions for computational linguists about the reliability of Google Somali spelling suggestions particularly when the search engine suggests an incorrect Somali spelling with fewer hits than a correctly spelt word.

 Click here to read the paper