Filters








1,730 Hits in 5.4 sec

Electoral Predictions with Twitter: A Machine-Learning approach

Mauro Coletto, Claudio Lucchese, Salvatore Orlando, Raffaele Perego
2015 Italian Information Retrieval Workshop  
Furthermore, we study how a machine learning approach can learn correction factors for those indicators.  ...  We investigate how to exploit and improve those indicators in order to reduce the bias of the Twitter users sample. We propose novel indicators and a novel content-based method.  ...  machine learning approach.  ... 
dblp:conf/iir/ColettoLOP15 fatcat:7z3lpfcx3zg23cigvhmwfuxe3q

Forecasting Social Unrest: A Machine Learning Approach

Sandile Hlatshwayo, Chris Redl
2021 IMF Working Papers  
The risk of social unrest is based on the probability of unrest in the following year derived from a machine learning model drawing on over 340 indicators covering a wide range of macro-financial, socioeconomic  ...  Shapley values indicate that the key drivers of the predictions include high current and prior levels of unrest, food price inflation and mobile phone penetration, which accord with previous findings in  ...  a discrete outcome, averaging predictions takes the form of a majority vote or averaging the probability of an event from each tree.  ... 
doi:10.5089/9781557758873.001 fatcat:buxbewqmc5gqpakicvams7hqve

A Survey on Sentimental Analysis Approaches using Machine Learning Algorithms

Anith Ashok, Dr. Sandeep Monga
2022 International Journal for Research in Applied Science and Engineering Technology  
In this work, a survey has been conducted on various work done in the past on sentiment analysis which includes opinion mining methods, machine learning based approaches and hybrid approaches which combines  ...  Some approaches which uses special statistical and machine learning models are included in separate section.  ...  Ghiassi (2018) [30] presented a Twitter Sentiment analysis using a Supervised Machine Learning Approach in a transferable Lexicon set.  ... 
doi:10.22214/ijraset.2022.42005 fatcat:ss2f2lpznzcktakldpbete3evu

Inferring Political Preferences from Twitter [article]

Mohd Zeeshan Ansari, Areesha Fatima Siddiqui, Mohammad Anas
2020 arXiv   pre-print
In this work, we chose to identify the inclination of political opinions present in Tweets by modelling it as a text classification problem using classical machine learning.  ...  Twitter is one of the most popular social media platforms enables us to perform domain-specific data preparation.  ...  Dandannavar (2017) research study focuses on the combination of a lexicon-based method and a machine learning-based algorithm to define a mixed approach for performing sentiment analysis [17] . V.  ... 
arXiv:2007.10604v1 fatcat:fynk2x6j4ve7foyylj4lxfalta

Electoral Forecasting Using a Novel Temporal Attenuation Model: Predicting the US Presidential Elections

Alexandru Topîrceanu
2021 Expert systems with applications  
scientific challenge with high social impact, as current data-driven methods try to efficiently combine statistics with economic indices and machine learning.  ...  A R T I C L E I N F O Keywords: election forecast temporal attenuation opinion polls social media US Presidential elections computational intelligence A B S T R A C T Electoral forecasting is an ongoing  ...  Appendix A. Supplementary data Supplementary data associated with this article can be found, in the online version, at https://doi.org/10.1016/j.eswa.2021.115289. A.  ... 
doi:10.1016/j.eswa.2021.115289 fatcat:rom3oeanhrcztjtldwt2fbqnlq

Analysis of Political Sentiment Orientations on Twitter

Mohd Zeeshan Ansari, M.B. Aziz, M.O. Siddiqui, H. Mehra, K.P. Singh
2020 Procedia Computer Science  
The Long Short Term Memory (LSTM) is employed to prepare the classification model and compare it with the classical machine learning models.  ...  The Long Short Term Memory (LSTM) is employed to prepare the classification model and compare it with the classical machine learning models.  ...  Research studies by A. Jain and P. Dandannavar (2017) focused on combining a lexical based approach with a learning based approach to form a hybrid approach to sentiment analysis [9] .  ... 
doi:10.1016/j.procs.2020.03.201 fatcat:xcqpilegcjcfppidry5jk2e5vq

Predicting the 2020 US Presidential Election with Twitter [article]

Michael Caballero
2021 arXiv   pre-print
Then, this research proposes a new method for electoral prediction which combines sentiment, from NLP on the text of tweets, and structural data with aggregate polling, a time series analysis, and a special  ...  One major sub-domain in the subject of polling public opinion with social media data is electoral prediction.  ...  This paper suggests that any approach to predict elections from Twitter data should be judged through four aspects: data collected, approach to deal with noise, methods of prediction, and overall evaluation  ... 
arXiv:2107.09640v1 fatcat:i3ggd2hpyfefziinrs7k2o3khe

Machine Learning-Based Sentiment Analysis for Twitter Accounts

Ali Hasan, Sana Moin, Ahmad Karim, Shahaboddin Shamshirband
2018 Mathematical and Computational Applications  
To deal with these challenges, the contribution of this paper includes the adoption of a hybrid approach that involves a sentiment analyzer that includes machine learning.  ...  Despite the use of various machine-learning techniques and tools for sentiment analysis during elections, there is a dire need for a state-of-the-art approach.  ...  Conclusions and Future Work This paper focuses on the adoption of various sentiment analyzers with machine-learning algorithms to determine the approach with the highest accuracy rate for learning about  ... 
doi:10.3390/mca23010011 fatcat:fdu2d6cshrc7tiwnrpluhnfd44

Bots and Gender Profiling on Twitter

Muhammad Hammad Fahim Siddiqui, Iqra Ameer, Alexander F. Gelbukh, Grigori Sidorov
2019 Conference and Labs of the Evaluation Forum  
In the proposed approach, we used a well-known bag of words model with different preprocessing actions (stemming, stop words removal, lowercase, etc.).  ...  The escalation in the use of social media facilities and proliferation in the fame of online social media websites such as Twitter, Facebook, LinkedIn, etc. directed to the growth of unwanted social bots  ...  Description of our Approach In this chapter, we defined our submitted approach considering the features and machine learning models used for this shared task.  ... 
dblp:conf/clef/SiddiquiAGS19 fatcat:xkbdnzhpcrdfhne2xl5staxu5i

Sentiment analysis model for Twitter data in Polish language [article]

Karol Chlasta
2019 arXiv   pre-print
The result data set was used to train and test four machine learning classifiers, to select these providing most accurate automatic tweet classification results.  ...  Each tweet from the text corpora was assigned a category based on its sentiment score.  ...  Data exploration and supervised machine learning on small datasets collected from a micro-blogging site like Twitter is possible with limited computing resources.  ... 
arXiv:1911.00985v1 fatcat:6ymavvqegfcpfean2ddirvh4we

Election Prediction on Twitter: A Systematic Mapping Study

Asif Khan, Huaping Zhang, Nada Boudjellal, Arshad Ahmad, Jianyun Shang, Lin Dai, Bashir Hayat, M. Irfan Uddin
2021 Complexity  
Identify, categorize, and present a comprehensive overview of the approaches, techniques, and tools used in election predictions on Twitter. Method.  ...  The majority of the studies employed supervised learning techniques, subsequently, lexicon-based approach SA, volume-based, and unsupervised learning.  ...  Perego, "Electoral predictions with Twitter: A machine- learning approach," CEUR Workshop Proc., vol. 1404, 2015. S-31 2 S. Salari, N. Sedighpour, V. Vaezinia, and S.  ... 
doi:10.1155/2021/5565434 fatcat:cwkd6rz4cndsboibxlpzvpnx2u

Predictive Analysis on Twitter: Techniques and Applications [article]

Ugur Kursuncu, Manas Gaur, Usha Lokala, Krishnaprasad Thirunarayan, Amit Sheth, I. Budak Arpinar
2018 arXiv   pre-print
In this chapter, we discuss techniques, approaches and state-of-the-art applications of predictive analysis of Twitter data.  ...  actions, and relate a few success stories.  ...  They compared their approach with state-of-the-art machine learning methods such as log-linear models.  ... 
arXiv:1806.02377v1 fatcat:gm5cqpmgvfggzgxgzocv4c3fqi

Predictive Analysis on Twitter: Techniques and Applications [chapter]

Ugur Kursuncu, Manas Gaur, Usha Lokala, Krishnaprasad Thirunarayan, Amit Sheth, I. Budak Arpinar
2018 Lecture Notes in Social Networks  
In this chapter, we discuss techniques, approaches and state-of-the-art applications of predictive analysis of Twitter data.  ...  actions, and relate a few success stories.  ...  They compared their approach with state-of-the-art machine learning methods such as log-linear models.  ... 
doi:10.1007/978-3-319-94105-9_4 fatcat:knquzcuqcjdjjguzq435nq5kni

Political Disaffection: a case study on the Italian Twitter community [article]

Corrado Monti, Alessandro Rozza, Giovanni Zappella, Matteo Zignani, Adam Arvidsson, Monica Poletti
2013 arXiv   pre-print
no questioning of the political regime" by exploiting Twitter data through machine learning techniques.  ...  In order to validate the quality of the time-series generated by the Twitter data, we highlight the relations of these data with political disaffection as measured by means of public opinion surveys.  ...  Moreover the authors show that the count of tweets mentioning a party or a candidate accurately reflected the election results suggesting a possible approach to perform an electoral prediction.  ... 
arXiv:1301.6630v2 fatcat:kni4li7aibby7i4fpgqwqbydpa

SENTIMENT ANALYSIS BASED ON TWITTER DATA ON VIOLENCE

Nihal Jumhare, Raja Rajeswari G, Balaji Jayakrishnan
2017 Asian Journal of Pharmaceutical and Clinical Research  
Algorithms can be developed so as to predict preferences of people to improve economic and marketing research. This paper presents a sentiment analysis on a recent scenario of Uri Attack.  ...  Due to the large volume of opinion-rich web resources such as Twitter, Facebook, blogs, and news available in digital form, and much of the current research is focusing on the area of sentiment analysis  ...  Although machine learning approach gives more accuracy, the semantic orientation approach is light weighted method and gives the respective sentiments easily.  ... 
doi:10.22159/ajpcr.2017.v10s1.20521 fatcat:muvlk4zmgrhfbipyzlani2ldgm
« Previous Showing results 1 — 15 out of 1,730 results