Fifth International Conference on Natural language Processing
(NLP - 2016)
Venue : Pullman Sydney Hyde Park, February 6 ~ 7, 2016 - Sydney, Australia
- Automatic Kurdish Dialects Identification
Hossein Hassani1,2 and Dzejla Medjedovic2 ,1University of Kurdistan Hewler, Iraq and 2Sarajevo School of Science and Technology, Bosnia and Herzegovina
Automatic dialect identification is a necessary Language Technology for processing multi-dialect languages in which the dialects are linguistically far from each other. Particularly, this becomes crucial where the dialects are mutually unintelligible. Therefore, to perform computational activities on these languages, the system needs to identify the dialect that is the subject of the process. Kurdish language encompasses various dialects. It is written using several different scripts. The language lacks of a standard orthography. This situation makes the Kurdish dialectal identification more interesting and required, both form the research and from the application perspectives. In this research, we have applied a classification method, based on supervised machine learning, to identify the dialects of the Kurdish texts. The research has focused on two widely spoken and most dominant Kurdish dialects, namely, Kurmanji and Sorani. The approach could be applied to the other Kurdish dialects as well. The method is also applicable to the languages which are similar to Kurdish in their dialectal diversity and differences.
- Stock Market Forecasting Using Data Mining Algorithms
Chinedu Egbuonu , Fairfield University , USA
ABSTRACTStock price forecasting is a venture that has earned many investors fortunes in the stock market. Predictably, the practice of stock price prediction has been as old as the advent of the stock market or the stock exchange. This practice follows an assumption that the fundamental information publicly available in the past has some predictive relationship to future stock returns.
This paper brings out the regression rules that are necessary in making factual prediction on stock price movements. It equally helps investors in the stock market in deciding which sector of the stock market is profitable for investment and what time period/time those investments should be made. In order to make accurate decisions, this paper tries to base its judgment on the decision tree classifier which is a technique in data mining. To build the model, the CRISP-DM (Cross Industry Standard for Data Mining) methodology is used over real historical data of over 500 stocks.