IRJET- Sentiment Analysis of Twitter Data using Python
0 likes62 views
1. The document discusses sentiment analysis of tweets using Python. It involves collecting tweet data using Twitter API and classifying the tweets as positive or negative using machine learning algorithms in Python. 2. It proposes using Anaconda Python to analyze tweets collected from Twitter and extract features from tweets like unigrams and bigrams to represent the tweet text. Various machine learning algorithms will then be used to conduct sentiment analysis and classify tweets as positive or negative. 3. The accuracy of individual models is limited, so the approach is to use the predictions from the top models to generate an ensemble model for improved accuracy of sentiment classification of tweets.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 510
Sentiment Analysis of Twitter Data using Python
Hetu Bhavsar1, Richa Manglani2
1,2GyanManjari Institute of Technology, GMIT, Bhavnagar-364001, India
-------------------------------------------------------------------------***------------------------------------------------------------------------
Abstract:- Twitter is a popular social networking website where users posts and interact with messages known as “tweets”. This
serves as a mean for individuals to express their thoughts or feelings about different subjects. Various different parties such as
consumers and marketers have done sentiment analysis on such tweets to gather insights into products or to conduct market
analysis. Furthermore, with the recent advancements in machine learning algorithms, the accuracy of our sentiment analysis
predictions is able to improve. We will attempt to conduct sentiment analysis on “tweets” usingvarious differentmachinelearning
algorithms.
Key Words: Sentiment analysis, Twitter data, Anaconda, python, positive, negative
1. INTRODUCTION
With the huge amount of increase in the web technologies, the no of people expressing their views and theopinionviawebare
increasing. This information is useful for everyone like businesses, governments and individuals with 500+ million tweets per
day, twitter is becoming a major source of information. Input to our model is the raw data extractedfromtweets.Forthesame,
we automate the process of tweet extraction and categorizing it into two categories i.e. positive or negative. The content in
twitter generated by the user is about different kinds of products, event, people and political affairs [7].
Performing sentiment analysis on tweets is considered best due to the following reasons:
1. Tweets are abstract in nature.
2. Analysis in real time can be done.
3. A vast variety of tweets for performing the analysis. [2]
2. LITERATURE SURVEY
1. Opinion Mining on Social Media Data [8]:
Po-Wei Liang et.al used Twitter API to collect data from twitter. Tweets which contain opinions were filtered out. Unigram
Naive Bayes model was developed for polarity identification. They also worked for elimination of unwanted features by using
the Mutual Information and Chi square feature extraction method. Finally,theapproachforpredictingthetweetsaspositiveor
negative did not give better accuracy by this method.
2. A Sentiment Analysis Prototype System for Social Network Data [3]:
This paper discusses a prototype system to enable automated opinion based analysis of social network data for evaluation of
the public social conscience of user provided topics and events.
3. Sentiment Analysis for Social Media [1]:
Sentiment Analysis is a problem of text based analysis, but there are some challenges that make it difficult as compared to
traditional text based analysis This clearly states that there is need of an attempt to work towards these problems and it has
opened up several opportunities for future research for handling negations, hidden sentiments identification, slangs ,
polysemy. However, the growing scale of data demands automatic data analysis techniques. In this paper,a detailed surveyon
different techniques used in Sentiment Analysis is carried out to understand the level of work.
4. Sentiment Analysis for Using Twitter DataSet [6]:
The research of sentiment analysis of Twitter data can be performed in different aspects. This papershowssentimentanalysis
types and techniques used to perform extraction of sentiment from tweets. In this survey paper, we have taken comparative
study of different techniques and approaches of sentiment analysis having twitter as a data.](https://image.slidesharecdn.com/irjet-v6i393-190809065757/85/IRJET-Sentiment-Analysis-of-Twitter-Data-using-Python-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 511
5. Sentiment Analysis of Tweets Using Machine Learning Approach [2]:
In this paper, SVM, ADABOOSTED DECISION TREE and DECISION TREE based hybrid sentiment classification model are
presented for improving the overall accuracy of the classifier in the classification of tweets.
3. OUR PROPOSAL
The proposed model of twitter data analysis will be implemented using Anaconda python.Anaconda isa freeandopensource
distribution of the Python and R programming languages for data science and machine learning relatedapplications.Itcanbe
installed on Windows, Linux, and MacOS. Conda is an open source, cross-platform, package management system.
The tweets can be analysed and characterized based on the emotions used by the social users. We attempt to classify the
polarity of the tweet where it is either positive or negative. If the tweet has both positive and negative elements, the more
dominant sentiment should be picked as the final label. We use the dataset from Kaggle which was crawled and labelled
positive/negative. The data provided comes with emoticons, usernames and hashtags which are requiredtobeprocessedand
converted into a standard form. It also needs to extract useful features from the text such unigrams and bigrams which is a
form of representation of the “tweet”.
4. CONCLUSION
The analysis of Twitter data is being done in different points of view to mine the opinion or sentiment.Ourproposedapproach
classify the tweets as Positive and Negative tweets which further helps in sentiment analysis and uses that sentiment analysis
for further decision making. For our prototype, Twitter API is utilized to gatherdata in real-time. Theprototype back-endtests
on retrieving and processing the API data indicate that it is successful in gathering large amounts of data from popular search
terms in real-time. We will use various machine learning algorithmstoconductsentimentanalysisusingtheextractedfeatures.
However, just relying on individual models did not give a high accuracy so we pick the top few models to generate a model.
REFERENCE
[1] Harshali P. Patil, Dr. Mohammad Atique, “Sentiment Analysis for Social Media: A Survey”, Department of Computer
Engineering Thakur College of Engineering & Technology Mumbai, India.
[2] Megha Rathi, Aditya Malik, Daksh Varshney, Rachita Sharma, Sarthak Mendiratta, “Sentiment Analysis of Tweets using
Machine Learning Approach”, Jaypee Institute of Information Technology JIIT Sec-62 Noida, India.
[3] Pitiphat Santidhanyaroj, Talha Ahmad Khan, “A SENTIMENT ANALYSIS PROTOTYPE SYSTEM FOR SOCIAL NETWORK
DATA,” Faculty of Engineering and Applied Science University of Regina Regina, Saskatchewan, Canada.
[4] Subramaniam.G, Ranjitha.M,” User Emotion Analysis using Twitter Data”, IFET COLLEGE OF ENGINEERING Cuddalore,
India.
[5] M.Trupthi, Suresh Pabboju,” SENTIMENT ANALYSIS ON TWITTER USING STREAMING API” 2017 IEEE 7th International
Advance Computing Conference
[6] Rasika Wagh, Payal Punde,” Sentiment Analysis usingTwitterDataset”,DepartmentofComputerScienceandIT, Dr.BAMU
Aurangabad, India.
[7] https://en.wikipedia.org/wiki/Twitter
[8] Po-Wei Liang, Bi-Ru Dai, “Opinion Mining on Social MediaData", IEEE 14th International Conference on Mobile Data
Management, Milan, Italy, June 3- 6, 2013, pp 91-96, ISBN: 978-1494673-6068-5
[9] P. D. Turney, “Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews,” in
Proceedings of the 40th annual meeting on association for computational linguistics, pp. 417–424, Association for
Computational Linguistics, 2002.](https://image.slidesharecdn.com/irjet-v6i393-190809065757/85/IRJET-Sentiment-Analysis-of-Twitter-Data-using-Python-2-320.jpg)
IRJET- Sentiment Analysis of Twitter Data using Python
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 510 Sentiment Analysis of Twitter Data using Python Hetu Bhavsar1, Richa Manglani2 1,2GyanManjari Institute of Technology, GMIT, Bhavnagar-364001, India -------------------------------------------------------------------------***------------------------------------------------------------------------ Abstract:- Twitter is a popular social networking website where users posts and interact with messages known as “tweets”. This serves as a mean for individuals to express their thoughts or feelings about different subjects. Various different parties such as consumers and marketers have done sentiment analysis on such tweets to gather insights into products or to conduct market analysis. Furthermore, with the recent advancements in machine learning algorithms, the accuracy of our sentiment analysis predictions is able to improve. We will attempt to conduct sentiment analysis on “tweets” usingvarious differentmachinelearning algorithms. Key Words: Sentiment analysis, Twitter data, Anaconda, python, positive, negative 1. INTRODUCTION With the huge amount of increase in the web technologies, the no of people expressing their views and theopinionviawebare increasing. This information is useful for everyone like businesses, governments and individuals with 500+ million tweets per day, twitter is becoming a major source of information. Input to our model is the raw data extractedfromtweets.Forthesame, we automate the process of tweet extraction and categorizing it into two categories i.e. positive or negative. The content in twitter generated by the user is about different kinds of products, event, people and political affairs [7]. Performing sentiment analysis on tweets is considered best due to the following reasons: 1. Tweets are abstract in nature. 2. Analysis in real time can be done. 3. A vast variety of tweets for performing the analysis. [2] 2. LITERATURE SURVEY 1. Opinion Mining on Social Media Data [8]: Po-Wei Liang et.al used Twitter API to collect data from twitter. Tweets which contain opinions were filtered out. Unigram Naive Bayes model was developed for polarity identification. They also worked for elimination of unwanted features by using the Mutual Information and Chi square feature extraction method. Finally,theapproachforpredictingthetweetsaspositiveor negative did not give better accuracy by this method. 2. A Sentiment Analysis Prototype System for Social Network Data [3]: This paper discusses a prototype system to enable automated opinion based analysis of social network data for evaluation of the public social conscience of user provided topics and events. 3. Sentiment Analysis for Social Media [1]: Sentiment Analysis is a problem of text based analysis, but there are some challenges that make it difficult as compared to traditional text based analysis This clearly states that there is need of an attempt to work towards these problems and it has opened up several opportunities for future research for handling negations, hidden sentiments identification, slangs , polysemy. However, the growing scale of data demands automatic data analysis techniques. In this paper,a detailed surveyon different techniques used in Sentiment Analysis is carried out to understand the level of work. 4. Sentiment Analysis for Using Twitter DataSet [6]: The research of sentiment analysis of Twitter data can be performed in different aspects. This papershowssentimentanalysis types and techniques used to perform extraction of sentiment from tweets. In this survey paper, we have taken comparative study of different techniques and approaches of sentiment analysis having twitter as a data.
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 511 5. Sentiment Analysis of Tweets Using Machine Learning Approach [2]: In this paper, SVM, ADABOOSTED DECISION TREE and DECISION TREE based hybrid sentiment classification model are presented for improving the overall accuracy of the classifier in the classification of tweets. 3. OUR PROPOSAL The proposed model of twitter data analysis will be implemented using Anaconda python.Anaconda isa freeandopensource distribution of the Python and R programming languages for data science and machine learning relatedapplications.Itcanbe installed on Windows, Linux, and MacOS. Conda is an open source, cross-platform, package management system. The tweets can be analysed and characterized based on the emotions used by the social users. We attempt to classify the polarity of the tweet where it is either positive or negative. If the tweet has both positive and negative elements, the more dominant sentiment should be picked as the final label. We use the dataset from Kaggle which was crawled and labelled positive/negative. The data provided comes with emoticons, usernames and hashtags which are requiredtobeprocessedand converted into a standard form. It also needs to extract useful features from the text such unigrams and bigrams which is a form of representation of the “tweet”. 4. CONCLUSION The analysis of Twitter data is being done in different points of view to mine the opinion or sentiment.Ourproposedapproach classify the tweets as Positive and Negative tweets which further helps in sentiment analysis and uses that sentiment analysis for further decision making. For our prototype, Twitter API is utilized to gatherdata in real-time. Theprototype back-endtests on retrieving and processing the API data indicate that it is successful in gathering large amounts of data from popular search terms in real-time. We will use various machine learning algorithmstoconductsentimentanalysisusingtheextractedfeatures. However, just relying on individual models did not give a high accuracy so we pick the top few models to generate a model. REFERENCE [1] Harshali P. Patil, Dr. Mohammad Atique, “Sentiment Analysis for Social Media: A Survey”, Department of Computer Engineering Thakur College of Engineering & Technology Mumbai, India. [2] Megha Rathi, Aditya Malik, Daksh Varshney, Rachita Sharma, Sarthak Mendiratta, “Sentiment Analysis of Tweets using Machine Learning Approach”, Jaypee Institute of Information Technology JIIT Sec-62 Noida, India. [3] Pitiphat Santidhanyaroj, Talha Ahmad Khan, “A SENTIMENT ANALYSIS PROTOTYPE SYSTEM FOR SOCIAL NETWORK DATA,” Faculty of Engineering and Applied Science University of Regina Regina, Saskatchewan, Canada. [4] Subramaniam.G, Ranjitha.M,” User Emotion Analysis using Twitter Data”, IFET COLLEGE OF ENGINEERING Cuddalore, India. [5] M.Trupthi, Suresh Pabboju,” SENTIMENT ANALYSIS ON TWITTER USING STREAMING API” 2017 IEEE 7th International Advance Computing Conference [6] Rasika Wagh, Payal Punde,” Sentiment Analysis usingTwitterDataset”,DepartmentofComputerScienceandIT, Dr.BAMU Aurangabad, India. [7] https://en.wikipedia.org/wiki/Twitter [8] Po-Wei Liang, Bi-Ru Dai, “Opinion Mining on Social MediaData", IEEE 14th International Conference on Mobile Data Management, Milan, Italy, June 3- 6, 2013, pp 91-96, ISBN: 978-1494673-6068-5 [9] P. D. Turney, “Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews,” in Proceedings of the 40th annual meeting on association for computational linguistics, pp. 417–424, Association for Computational Linguistics, 2002.