DETERMINATION OF QUALITY OF INDIVIDUAL MENU ITEMS FROM RESTAURANT REVIEWS USING SENTIMENT ANALYSIS
DOI:
https://doi.org/10.24867/07BE09JoksimovicKeywords:
text mining, text classification, natural language processing, sentiment analysis, restaurant reviewsAbstract
This paper presents one approach for extraction of parts of restaurant reviews which contain information about opinion of certain menu item and classification of those segments by expressed sentiment as positive, negative or neutral using several machine learning algorithms. Text segments which contain food mentions were generated using lexical relationships between words in reviews and several preprocessing techniques were applied. Afterwards, sentiment analysis was done using several machine learning models. Data was acquired from the website Donesi.com and manually annotated. All used models were evaluated.
References
[1] www.donesi.com
[2] Jason Huggins, et al, 2004. Selenium,
https://www.seleniumhq.org
[3] Leonard Richardson 2014, BeautifulSoup4
https://www.crummy. com/software/BeautifulSoup
[4] Ljubesic, Nikola, Tomaz Erjavec and Darja Fiser. “Corpus-Based Diacritic Restoration for South Slavic Languages.” LREC (2016).
[5] Ljubesic, Nikola and Tomaz Erjavec. “Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene.” LREC (2016).
[6] Ljubesic, Nikola, Filip Klubicka, Zeljko Agic and Ivo-Pavao Jazbec. “New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian.” LREC (2016).
[7] Agic, Zeljko and Nikola Ljubesic. “Universal Dependencies for Croatian (that work for Serbian, too).” BSNLP@RANLP (2015).
[8] Fišer, D., Ljubešić, N. & Erjavec, T. Lang Resources & Evaluation (2018). https://doi.org/10.1007/s10579-018-9425-z
[9] Milosevic, Nikola “Stemmer for Serbian Language. ” CoRR abs/ 1209.4471 (2012): n. pag.
[10] Universal Dependencies,
https://universaldependencies.org/#language-u
[11] GridSearchCV, Scikit-learn
https://scikit-learn.org/stable/modules/generated/-sklearn.model_selection.Grid-SearchCV.html
[12] Leung K. M. (2007). “Naive Bayesian Classifier”,
Polytechnic University, Department of Computer Science, Finance and Risk Engineering.
[13] Support Vector Machines (SVM), Statsoft,
http://www.statsoft.com/Textbook/Support-Vector-Machines
[14] Breiman L. (2001) “Random Forests, Machine
Learning”, Vol. 45. Issue 1, pp. 5-32.
[15] Logistic Regression Scikit-learn,
https://scikit-learn.org/stable/modules/generated/-sklearn.linear_model.Logistic-Regression.html
[2] Jason Huggins, et al, 2004. Selenium,
https://www.seleniumhq.org
[3] Leonard Richardson 2014, BeautifulSoup4
https://www.crummy. com/software/BeautifulSoup
[4] Ljubesic, Nikola, Tomaz Erjavec and Darja Fiser. “Corpus-Based Diacritic Restoration for South Slavic Languages.” LREC (2016).
[5] Ljubesic, Nikola and Tomaz Erjavec. “Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene.” LREC (2016).
[6] Ljubesic, Nikola, Filip Klubicka, Zeljko Agic and Ivo-Pavao Jazbec. “New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian.” LREC (2016).
[7] Agic, Zeljko and Nikola Ljubesic. “Universal Dependencies for Croatian (that work for Serbian, too).” BSNLP@RANLP (2015).
[8] Fišer, D., Ljubešić, N. & Erjavec, T. Lang Resources & Evaluation (2018). https://doi.org/10.1007/s10579-018-9425-z
[9] Milosevic, Nikola “Stemmer for Serbian Language. ” CoRR abs/ 1209.4471 (2012): n. pag.
[10] Universal Dependencies,
https://universaldependencies.org/#language-u
[11] GridSearchCV, Scikit-learn
https://scikit-learn.org/stable/modules/generated/-sklearn.model_selection.Grid-SearchCV.html
[12] Leung K. M. (2007). “Naive Bayesian Classifier”,
Polytechnic University, Department of Computer Science, Finance and Risk Engineering.
[13] Support Vector Machines (SVM), Statsoft,
http://www.statsoft.com/Textbook/Support-Vector-Machines
[14] Breiman L. (2001) “Random Forests, Machine
Learning”, Vol. 45. Issue 1, pp. 5-32.
[15] Logistic Regression Scikit-learn,
https://scikit-learn.org/stable/modules/generated/-sklearn.linear_model.Logistic-Regression.html
Downloads
Published
2020-02-22
Issue
Section
Electrotechnical and Computer Engineering
