sep=/; start="" data=/home/ninat/kubhist #data: we are using the kubhist export xml files: e.g., \digidaily-blekingsposten\export code=/home/ninat/retorik/code #code: from where the jar files are read queryList=/home/ninat/retorik/input/kung.txt #queryList: the terms used for keeping sentences output=/home/ninat/retorik/text #output: where the text and corresponding dictionary is located for each time period and set of query terms #the query term is chosen as the first term from queryList logfile=/home/ninat/retorik/logfile.txt sentenceoutput=/home/ninat/retorik/sentences #sentenceoutput: where all sentences with at least one query term end up marked as positve/negative/both/neutral logfile=/home/ninat/retorik/logfile.txt #MCpositive,MCnegative: location and first part of file name for statistics on the most common positive and negative #terms, for each period separately as well as total for the entire corpus. MCpositive=/home/ninat/retorik/OMstats/mostCommonPositive MCnegative=/home/ninat/retorik/OMstats/mostCommonNegative queryList=/home/ninat/retorik/input/kung.txt #queryList: the terms used for keeping sentences positive=/home/ninat/retorik/input/positiv_bring_singletokens.txt negative=/home/ninat/retorik/input/negativ_bring_singletokens.txt #positve,negative: the list of all terms considered positive and negative stoplist_positive=/home/ninat/retorik/input/positive_stoplist.txt stoplist_negative=/home/ninat/retorik/input/negative_stoplist.txt #stoplist_positive, stoplist_negative: lists of words that should be excluded from the positive and negative lists, assuming they exist. maxLinesPerYear=10000 #filenameFilter used for keeping files to read data from. fileNameEndingfilter used for excluding files fileNameFilter=digidaily fileNameEndingfilter=bz2 #graphN1 and N2 are used for naming of graphs graphN1=Graph_dict_ graphN2=_Kubhist_NP.txt minDictFreq=0 #nuberOfYears is used for creating time periods, 10 equals a decade. numberOfYears=10 #startYear only if you want to skip making some graphs. startYear=1920