Big Data Training for Doctoral Students

Thursday (27/1) and Friday (28/1) the Center for Indigenous and Cultural Psychology (CICP) in collaboration with the UGM Psychology Doctoral Study Program held a webinar with the title “Big Data Training for Doctoral Students”. This event discusses the application of data collection and analysis techniques from social media in research in the field of psychology. This event is specifically for students of the UGM Psychology Doctoral Study Program.

On Thursday the event took place from 13.00 WIB to 16.00 WIB. Meanwhile, on Friday the event will run from 14.00 WIB to 16.00 WIB. The event was attended by 25 participants of doctoral students from the Faculty of Psychology, UGM.

The event was opened by Haidar Buldan Thontowi, S.Psi., M.A., Ph.D. lecturer at the UGM Faculty of Psychology and the head of the UGM Center of Indigenous and Cultural Psychology (CICP). In addition to opening the event, Buldan also provided material on introduction to Big Data and Analytics.

In his presentation, Buldan explained about the possibility of using data from social media in psychological research. Starting from his introduction to twitter data as a basis for analyzing his research data when completing his doctoral program, Buldan said that there are several advantages or advantages when using social media data as research data.

“So, when distributing surveys there is a tendency that people might fill in according to social norms. (On the other hand) when I see it on Twitter, the emotion comes out. So, they use harsh words or whatever they are free to do that,” said Buldan.

Next, Buldan explained about some software that can be used to retrieve data from social media. Not to forget, theoretical books on the use of social media data were also introduced in this session. Finally, Buldan also explained about the research using Big Data that is currently underway at CICP, which include “Coping During a Pandemic: Twitter Analysis of Psychosocial Responses to the Impact of Covid-19 in Indonesia” and “Changing Risk Perception in the COVID-19”. Pandemic: A Sentiment Analysis of Two Lockdown Periods in Indonesia”.

The next session continued with an explanation of the Twitter data retrieval technique by Syurawasti Muhiddin, S.Psi., M.A. In this session, participants are invited to learn step by step taking data from Twitter social media legally. Therefore, Shura started his training by teaching participants how to create a Twitter API (Application Programming Interface) because it is the main requirement to be able to legally retrieve Twitter data.

Then in the third session, Lalu Tarangga Arief Gunawan presented a training material for Data Preprocessing and Data Cleaning. At this stage the training participants are invited to understand the parts of the data that are important and not important to be separated and cleaned. Some of the techniques he teaches include case folding, URL cleaning, mentions, hashtags, reserve words, emoji, smileys, numbers, removing punctuation marks, spelling correction, and cleaning stop words.

On the second day of the event, the presentation was filled with material about the Orange Application by Yunita Sari, S.Kom., M.Sc., Ph.D. In this closing session, Yunita invites participants to learn from the introduction of the Orange application, data retrieval using the Orange application, and finally data analysis using the Orange application. Yunita invites participants to directly apply what they teach in the Orange application through the data that has been provided.

 

Photo by Adeolu Eletu on Unsplash