Python Text Analytics

Python Text Analytics was written by Indian data scientist Dipanjan Sarkar and translated by Yan Longchuan, Gao Dequan, and Li Junting. China Machine Press introduced and published it in 2018 as part of the "Data Science and Engineering Technology Series." The original title is Text Analytics with Python: A Practical Real-World Approach to Gaining Actionable Insights from Your Data. The book follows a structured "concept-method-code implementation" approach: it first explains the fundamentals of natural language and linguistics, including words, phrases, clauses, syntactic structures, semantic relations, and semantic networks, and introduces how text corpora are annotated and accessed, sketching the overall landscape of natural language processing tasks such as machine translation, speech recognition, question answering, text summarization, and text classification; it then reviews Python syntax, data structures, functional programming features, and common text processing methods to lay the groundwork for later hands-on work. The main body unfolds around the core workflow of text analytics: tokenization and sentence segmentation, text normalization (cleaning, case conversion, stopword removal, stemming, and lemmatization), part-of-speech tagging, and syntactic and structural parsing techniques such as shallow parsing, dependency parsing, and constituency parsing; it then further explains the complete chain of text classification—feature engineering, vectorization methods such as bag-of-words and TF-IDF, classifiers such as Naive Bayes and support vector machines, and model evaluation approaches. The book also covers topics including text summarization, text similarity and clustering, and semantic and sentiment analysis, and uses open-source libraries such as nltk, gensim, scikit-learn, spaCy, and Pattern, together with cases such as news article classification, topic modeling of app and game reviews, movie synopsis clustering, and movie review sentiment analysis, to ground the algorithms in runnable code. The book has seven chapters and about 273 pages, and is suitable as a bridge reading for readers who want to move from beginner to intermediate level in applying natural language processing and machine learning techniques to real-world text data processing.