0 ×

02_​NetworkAnalytics_​meets_​TextProcessing

Workflow

Network creation and analysis Data loading Text processing and sentiment analysis Visualization of combined results from text and networkmining General Information Press the green double arrow above to run the complete workflow. The grey nodes are metanodes that contain a sub workflow which you can inspect and change to your needs by doing adouble-click. The Table and File Reader nodes use a workflow relative path to read the files e.g. SlashdotRawData.table or subjclueslen1-HLTEMNLP05.zip which are located in the data folder. Workflow Description The goal of the text processing part of the workflow is to identify the general mood of a user e.g. positive, negative or neutral based on the sentiment of its posts and comments. The goal of thenetwork analysis part is to compute the social status e.g. leader or follower of a user in the forum community. The visualization part condenses the results from both areas into a single scatterplotthat visualizes the social status as well as the general mood of the users in the slashdot data set.Required plugins:- KNIME Network Mining (KNIME Labs Extensions)- KNIME Textprocessing (KNIME Labs Extensions) Data Description The SlashdotRawData.table contains the raw forum information such as the post id, post user, post content and all the comments for a given post including the post user. The text mining isperformed on documents created from the textual information e.g. post body and comment body into a KNIME document. The network consists of the links based on the post and comment userinformation.Workflow created on 08/01/2016 on KNIME 3.1 Network Analytics meets Text ProcessingThis workflow combines two pre-processing techniques: network analytics and text processing.The goal of the text processing part is to identify the general mood of a user e.g. positive,negative or neutral based on the sentiment of its posts and comments. The goal of the network analytics part is to compute the social status e.g. leader or follower of a user in the forumcommunity. The visualization part condenses the two result sets into a single scatterplot that visualizes the social status as well as the general mood of the users for the slashdot data set. SlashdotSubjectivity corpuslink post user with referenced post/threaduserextract the largestsubnet from thenetworkedge table weighted by count of postsFilter article and comments of anonymous userspreprocessingcompute authority & hubscoreNode 219accumulation ofpositive and negative word frequencies, user scoring and binningTag Cloud ofselected authortag positive wordstag negative wordsauthorson a scatter plotauth score vs. hub scorecolored by sentimentTag Clouds ofmost positive andmost negative author Table Reader File Reader Object Inserter Extract largestcomponent Create edge table Preprocessing Joiner Subjectivity Corpus Network Analyzer Document Creation User Scoring Tag Cloud ofSelected Author Dictionary Tagger Dictionary Tagger Scores & Sentimenton Scatter Plot Most Positive /Negative Author Tag Cloud Network creation and analysis Data loading Text processing and sentiment analysis Visualization of combined results from text and networkmining General Information Press the green double arrow above to run the complete workflow. The grey nodes are metanodes that contain a sub workflow which you can inspect and change to your needs by doing adouble-click. The Table and File Reader nodes use a workflow relative path to read the files e.g. SlashdotRawData.table or subjclueslen1-HLTEMNLP05.zip which are located in the data folder. Workflow Description The goal of the text processing part of the workflow is to identify the general mood of a user e.g. positive, negative or neutral based on the sentiment of its posts and comments. The goal of thenetwork analysis part is to compute the social status e.g. leader or follower of a user in the forum community. The visualization part condenses the results from both areas into a single scatterplotthat visualizes the social status as well as the general mood of the users in the slashdot data set.Required plugins:- KNIME Network Mining (KNIME Labs Extensions)- KNIME Textprocessing (KNIME Labs Extensions) Data Description The SlashdotRawData.table contains the raw forum information such as the post id, post user, post content and all the comments for a given post including the post user. The text mining isperformed on documents created from the textual information e.g. post body and comment body into a KNIME document. The network consists of the links based on the post and comment userinformation.Workflow created on 08/01/2016 on KNIME 3.1 Network Analytics meets Text ProcessingThis workflow combines two pre-processing techniques: network analytics and text processing.The goal of the text processing part is to identify the general mood of a user e.g. positive,negative or neutral based on the sentiment of its posts and comments. The goal of the network analytics part is to compute the social status e.g. leader or follower of a user in the forumcommunity. The visualization part condenses the two result sets into a single scatterplot that visualizes the social status as well as the general mood of the users for the slashdot data set. SlashdotSubjectivity corpuslink post user with referenced post/threaduserextract the largestsubnet from thenetworkedge table weighted by count of postsFilter article and comments of anonymous userspreprocessingcompute authority & hubscoreNode 219accumulation ofpositive and negative word frequencies, user scoring and binningTag Cloud ofselected authortag positive wordstag negative wordsauthorson a scatter plotauth score vs. hub scorecolored by sentimentTag Clouds ofmost positive andmost negative author Table Reader File Reader Object Inserter Extract largestcomponent Create edge table Preprocessing Joiner Subjectivity Corpus Network Analyzer Document Creation User Scoring Tag Cloud ofSelected Author Dictionary Tagger Dictionary Tagger Scores & Sentimenton Scatter Plot Most Positive /Negative Author Tag Cloud

Download

Get this workflow from the following link: Download

Nodes

02_​NetworkAnalytics_​meets_​TextProcessing consists of the following 140 nodes(s):

Plugins

02_​NetworkAnalytics_​meets_​TextProcessing contains nodes provided by the following 8 plugin(s):