Korištenje Pythona u analizi sentimenta

undergraduate thesis

• Title (english): Using Python for sentiment analysis
• Author: Anamaria Tokić
• Mentor: Tomislava Lauc (mentor)
• Committee member: Tomislava Lauc (član povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Sanja Kišiček (predsjednik povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2022-09-05, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Mišljenja, naša vlastita, ali i ona drugih ljudi, uvelike utječu na naše ponašanje i donošenje odluka. Želimo li, na primjer, kupiti novi proizvod prvo ćemo posegnuti za osvrtima, tj. mišljenjima drugih ljudi o njemu. Analiza sentimenta ili dubinsko pretraživanje mišljenja se odnosi na računalnu obradu prirodnog jezika kojom se analiziraju stavovi i mišljenja pojedinaca o nekom proizvodu, temi, usluzi i slično. Ovaj će se završni rad baviti primjenom programskog jezika Python u analizi sentimenta. Posebno će se koristiti biblioteke Pandas, NLTK i Scikit-learn te njihove metode i funkcije. Također, bit će prikazani klasifikatori, s posebnim osvrtom na Naivni Bayesov klasifikator te logističku regresiju. Korpus koji će biti korišten u primjerima je korpus osvrta s Amazona koji je preuzet s poveznice: https://www.coursera.org/learn/python-text-mining/resources/d9pwm

Abstract (english)

Opinions, our own and those of other people, influence our behavior and decision-making. If, for example, we want to buy a new product, we will first look for reviews, i.e. other people's opinion about it. Sentiment analysis or opinion mining refers to computer processing of natural language, which analyzes the attitudes and opinions of individuals about e.g. a product, topic or a service. This paper will deal with the application of the Python programming language in sentiment analysis. In particular with Pandas, NLTK and Scikit-learn libraries and their methods and function. Also, classifiers will be presented, with a special focus on the Naive Bayes classifier and logistic regression. The corpus that will be used in the examples is the review corpus from Amazon downloaded from the links: https://www.coursera.org/learn/python-text-mining/resources/d9pwm

• Keywords: analiza sentimenta; Python; pandas; NLTK; scikit; klasifikacija
• Keywords (english): seniment analysis; Python; pandas; NLTK; scikit; clasification
• Language: croatian
• URN:NBN: urn:nbn:hr:131:524660
• Study programme: Title: Information Sciences; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-09-15 09:01:14