Function reference • bitTA

Tools for Text Analytics Tools that support “Natural Language Processing” for text analytics.
`bitTA-package`	3rd party package of Bit2R with TA function
텍스트 데이터 전처리 기능
`filter_text()`	Filter data based on string matches of text data
`replace_text()` `concat_text()` `split_text()` `remove_text()`	Replace/remove/join/separate strings in text data
`get_meta()` `set_meta()`	Meta information processing for text data preprocessing
`get_spacing()`	Korean automatic spacing
`get_ngrams()`	Tokenization with N-gram
`tokenize_noun_ngrams()`	N-gram Tokenizer
`unnest_noun_ngrams()`	Wrapper around unnest_tokens for n-grams of noun
`collapse_noun()`	Extract Collapsed Noun
텍스트 데이터 탐색 기능
`explore_docs()`	Text Data Explorer
형태소분석 기능
`install_mecab_ko()`	Installation of Eunjeonhan morpheme analyzer and dic
`regist_mecab_ko()`	Register the path where Mecab-Ko is installed
`morpho_mecab()`	part-of-speech tagger based on mecab-ko morphology analyzer
감성분석 기능
`get_opinion()`	KOSAC(Korean Sentiment Analysis Corpus) Sentiment Analysis
텍스트 데이터
`buzz`	Naver Cafe Post Scraping Data
`rest_area`	Highway rest area related buzz
`president_speech`	President's Speech
`movie_ratings_train` `movie_ratings_test`	Naver sentiment movie corpus v1.0
`polarity`	KOSAC(Korean Sentiment Analysis Corpus) sentiment dictionary
`sentiment_dic`	KNU Korean Sentiment Dictionary

Reference