Bu kaydın yasal hükümlere uygun olmadığını düşünüyorsanız lütfen sayfa sonundaki Hata Bildir bağlantısını takip ederek bildirimde bulununuz. Kayıtlar ilgili üniversite yöneticileri tarafından eklenmektedir. Nadiren de olsa kayıtlarla ilgili hatalar oluşabilmektedir. MİTOS internet üzerindeki herhangi bir ödev sitesi değildir!

Sentiment Analysis In Social Media: A Comparative Study

BROWSE_DETAIL_CREATION_DATE:

BROWSE_DETAIL_IDENTIFIER_SECTION

BROWSE_DETAIL_TYPE: Thesis

BROWSE_DETAIL_SUB_TYPE: Masters

BROWSE_DETAIL_PUBLISH_STATE: Unpublished

BROWSE_DETAIL_FORMAT: PDF Document

BROWSE_DETAIL_LANG: English

BROWSE_DETAIL_CREATORS: Gebreyesus, Yasmin Tesfaldet (Author),

BROWSE_DETAIL_CONTRIBUTERS: Yazıcı, Ali (Advisor),

BROWSE_DETAIL_TAB_KEYWORDS

Sentiment Analysis, Big Data, Supervised Classification, Spark, Spark ML, Twitter, Deep Learning 


BROWSE_DETAIL_TAB_ABSTRACT

Sentiment Analysis is the task of detecting and classifying the polarity of textual content, such as social media posts. Sentiment analysis for Twitter has been a popular topic in academia whereby studies are being conducted using openly available datasets. The state-of-the-art results are achieved by a wide range of techniques, including classical Machine Learning classifiers such as Support Vector Machines (SVM) and the recent advancements in Neural Networks, namely, Deep Learning models. In this thesis, we study large scale Sentiment Analysis for Social Media using Big Data frameworks. Our motivation comes from the observation that there is a dearth of studies exploring the impact of the big-data criteria on the performance of classifiers. The goal is not to simply achieve best accuracy, but rather to study the behavior of classic classifier algorithms when incorporated with big data frameworks. To this end, we implement various Sentiment Analysis models with and without big data frameworks and compare the performance benefits and trade-offs. We report on several classification evaluation metrics and additionally keep track of computation time to observe the advantages of using big data frameworks (Apache Spark) based models. Particularly, we set two experimental scenarios using same dataset and feature engineering techniques with the only difference being the big-data framework. 


BROWSE_DETAIL_TAB_TOC



BROWSE_DETAIL_TAB_DESCRIPTION



BROWSE_DETAIL_TAB_RIGHTS



BROWSE_DETAIL_TAB_NOTES



BROWSE_DETAIL_TAB_REFERENCES


BROWSE_DETAIL_TAB_REFERENCED_BYS

BROWSE_DETAIL_GOTO_LIST

 

TEXT_STATS

  • TEXT_RECORD_STATS
    • TEXT_STATS_THIS_MONTH: 0
    • TEXT_STATS_TOTAL: 2441
  • TEXT_ONLINE_STATS
    • TEXT_ONLINE_STATS_TOTALONLINEVISITOR: 61
    • TEXT_ONLINE_STATS_TOTALONLINEUSER: 0
    • TEXT_STATS_TOTAL: 61

LINK_STATS