Social Computing 2020

Social Computing Course at TLU in 2020

Enrollment for this course ended on September 17, 2020.
In case of questions, please contact the facilitator.

Blog posts

Comments

December 10, 2020

Machine Learning Classification with RapidMiner – Data Analysis Project 2

10.12.2020 16:14 by Girish Nalawade
Introduction to dataset The dataset chosen to work on was Spam SMS Detection. This dataset consists of many SMS which were marked as either spam or ham (not spam). The dataset had 4259 rows and 5 columns. Some of the SMS
read more

Data Analysis with Rapidminer

10.12.2020 12:12 by Ali Haririan
A short introduction of the dataset (including descriptive statistics). We selected the IMDB dataset which contained movie reviews. The dataset consisted of two rows, one for the reviews and one for sentiment classification. T
read more

Social Network Analysis with Gephi – Data Analysis Project 1

10.12.2020 1:42 by Girish Nalawade
Introduction to dataset The dataset chosen to work on was about coauthorships in network science. The dataset consists of the coauthorship network of scientists working on network theory and experiment, as compiled by M.
read more

December 9, 2020

Spam Emails Detection using Rapid Miner

09.12.2020 8:20 by Farshad Farahnakian
Written by Farshad Farahnakian Introduction to Rapid Miner Machine learning and Data Science have been receiving so much attention in many fields from military service and scientific applications to entertainme
read more

December 7, 2020

Machine Learning Classification with RapidMiner

07.12.2020 16:41 by Simay Akin
IntroductionWe chose the Dataset about Twitter Hate Speech because we both use Twitter and thought it would be interesting to work with a topic we are familiar with. The dataset consisted of 26.304 rows and four columns na
read more

Data Analysis Project 2: Twitter Hate Speech Detection

07.12.2020 16:31 by Jeffrey Pillmann
Introduction We chose the Dataset about Twitter Hate Speech because we both use Twitter and thought it would be interesting to work with a topic we are familiar with. The dataset consisted of 26.304 rows and four columns
read more

Machine Learning Classification with RapidMiner

07.12.2020 15:47 by Mahsa Rezaeipour
Introduction The dataset we selected for the classification with Rapidminer is Spam Emails detection. The set consisted of emails and the label values of 0 and 1. The emails with value 1 represent spam and 0 sh
read more

Data Analysis Project 2 : Machine Learning Classification with RapidMiner

07.12.2020 15:42 by Vishnu Raj Maniyil
Introduction The dataset we selected for the classification with Rapidminer is Spam Emails detection. The set consisted of emails and the label values of 0 and 1. The emails with value 1 represent the spam and
read more

November 30, 2020

Data Analysis Project 1: Social Network Analysis with Gephi

30.11.2020 21:46 by Mahsa Rezaeipour
The data set we worked on was the page-page graph of verified Facebook sites.The nodes represent official Facebook pages while the edges represent the mutual likes between the pages. The mutual likes between the organization also show mutual s
read more

Data Analysis Project 1 : Social Network Analysis with Gephi

30.11.2020 20:16 by Vishnu Raj Maniyil
Data Analysis Project 1 : Social Network Analysis with Gephi The data set we worked was the page-page graph of verified Facebook sites.  The nodes represent official Facebook pages while the edges represent the mutual like
read more

December 31, 2020

Girish Srinivas Rao Nalawade to Girish Nalawade

31.12.2020 9:50
In reply to Tobias. Thank you, Tobias.
read more

December 29, 2020

Tobias to Girish Nalawade

29.12.2020 15:40
Visualisation was very good. You chose betweenness centrality as something to visualize which nicely showed the bridges between communities.
read more

Tobias to Kärol-Milaine Jürgenson

29.12.2020 15:37
Great work and thank you also for the substantial manual work you have put into this. We may reuse it for a future class. Also it was very nice that you imported a bi-partite graph, as this got us a
read more

Tobias to Ali Haririan

29.12.2020 15:34
Good overall and you answered your question in the end. Maybe some more informed choices on the visualization would have been good, e.g. using different attributes than degree for color and size of
read more

December 18, 2020

Girish Srinivas Rao Nalawade to Girish Nalawade

18.12.2020 20:13
In reply to Gerti Pishtari. Thank you, Gerti.
read more

December 13, 2020

ali haririan to Ali Haririan

13.12.2020 17:31
In reply to Gerti Pishtari. Tha
read more

December 12, 2020

Farshad Farahnakian

12.12.2020 14:53
In reply to Gerti Pishtari. I really appreciate for your feedback, It is really helpful for me to understan
read more

Farshad Farahnakian

12.12.2020 14:46
In reply to Gerti Pishtari. Thanks Gerti for your feedback!
read more

Gerti Pishtari to Farshad Farahnakian

12.12.2020 13:32
Good report overall! A couple of considerations. 1. Usually the automatic process is used to understand which might be the more appropriate algorithms for the current data and then the best
read more

Gerti Pishtari to Farshad Farahnakian

12.12.2020 13:27
The report is well written! Sometimes, if there are many nodes, you might filter only the ones with higher degree or centrality to easily understand the relevant data and then create visualisations
read more