A study on text miningon twitter : identifying opinion and detecting different forms of speech using Writing patterns (本文)
Mondher Bouazizi · Institutional Repositories DataBase (IRDB) · 2019
Over the last two decades, online user-generated content has been exponentially increasing.With its increase, a proportionally increasing interest has been attributed to this data from the research community.While several works have been targeting different types of user-generated media such as photos, videos and audio content, text has always attracted most of the attention for Undertaking this PhD has been a truly life-changing experience.It would not have been possible to do without the support, guidance and encouragement of many people.First and foremost, I would like to express my deepest and sincere gratitude to my supervisor Prof. Tomoaki Ohtsuki for the continuous support and encouragement that he gave me.Without his patience, motivation and immense knowledge, this PhD would not have been achievable.His advice was crucial to undertake new research challenges and keep persevering even in hard times when results were hard to obtain.I am deeply grateful for all the empowerment I received under his supervision that let me define my own pace.The committee members Dr. Tony Quek, Prof. Iwao Sasase and Prof. Masaaki Ikehara deserve a special mention, for their precious time and advice that