Towards Analyzing Saudi Tweets

摘要

Recently Arabic dialects are receiving attention from the NLP research community due to their high usage in social media. One of the challenges of sentiment analysis of social media is the use of dialects. Since our ongoing research is on sentiment analysis of Saudi tweets, we conduct a pilot study to discover the percentage of Modern Standard Arabic (MSA) use by Saudi tweeters. The preliminary results show that 80% of the tweets used in the study are in MSA. Some phenomena found about the use of dialect in Saudi tweets are highlighted.