Does the Strength of Sentiment Matter? A Regression Based Approach on Turkish Social Media

Date

2017-06-23

Author

Ertugrul, Ali Mert
Onal, Itir
Acartürk, Cengiz

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

94
views

0
downloads

Social media posts are usually informal and short in length. They may not always express their sentiment clearly. Therefore, multiple raters may assign different sentiments to a tweet. Instead of employing majority voting which ignores the strength of sentiments, the annotation can be enriched with a confidence score assigned for each sentiment. In this study, we analyze the effect of using regression on confidence scores in sentiment analysis using Turkish tweets. We extract hand-crafted features including lexical features, emoticons and sentiment scores. We also employ word embedding of tweets for regression and classification. Our findings reveal that employing regression on confidence scores slightly improves sentiment classification accuracy. Moreover, combining word embedding with hand-crafted features reduces the feature dimensionality and outperforms alternative feature combinations.

Subject Keywords

Sentiment analysis, Regression, Word embedding, Word2vec

URI

https://hdl.handle.net/11511/32610

DOI

https://doi.org/10.1007/978-3-319-59569-6_16

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

Utilizing Word Embeddings for Result Diversification in Tweet Search Onal, Kezban Dilek; Altıngövde, İsmail Sengör; Karagöz, Pınar (2015-12-04) The performance of result diversification for tweet search suffers from the well-known vocabulary mismatch problem, as tweets are too short and usually informal. As a remedy, we propose to adopt a query and tweet expansion strategy that utilizes automatically-generated word embeddings. Our experiments using state-of-the-art diversification methods on the Tweets2013 corpus reveal encouraging results for expanding queries and/or tweets based on the word embeddings to improve the diversification performance in...
Twitter Sentiment Analysis Experiments Using Word Embeddings on Datasets of Various Scales Arslan, Yusuf; Kucuk, Dilek; Birtürk, Ayşe Nur (2018-06-15) Sentiment analysis is a popular research topic in social media analysis and natural language processing. In this paper, we present the details and evaluation results of our Twitter sentiment analysis experiments which are based on word embeddings vectors such as word2vec and doc2vec, using an ANN classifier. In these experiments, we utilized two publicly available sentiment analysis datasets and four smaller datasets derived from these datasets, in addition to a publicly available trained vector model over ...
A novel pre-processing workflow for popularity prediction in social media Yıldırım, Hüseyin Buğra; Taşkaya Temizel, Tuğba; Department of Information Systems (2021-9-10) Users in Twitter are in continuous interaction with each other through posts and reactions such as likes and retweets. Tweets often get a little reaction from people, with only a few of them receiving a prominent response. Thus, reaction numbers result in having a heavy right-skewed distribution. Furthermore, some tweets show unexpected response performance that cannot be depicted by standard features and are often dependent on extraordinary situations such as being the first reporter and mass reaction. Hea...
Irony detection on Turkish microblog texts Taşlıoğlu, Hande; Karagöz, Pınar; Department of Computer Engineering (2014) Social media is the new trend for expressing personal ideas to other people. Since people are sharing real time messages about their opinions on diverse topics, there exists huge amount of raw data to analyze. Thus, manual classification of these data becomes impossible. Irony, as a simple definition, is creative use of language and attracts computer scientists’ attention lately. Automatic detection of irony on microblog texts is not a trivial task. Texts of microblogs can have limited number of characters,...
Detecting User Emotions in Twitter through Collective Classification İLERİ, İBRAHİM; Karagöz, Pınar (2016-11-11) The explosion in the use of social networks has generated a big amount of data including user opinions about varying subjects. For classifying the sentiment of user postings, many text-based techniques have been proposed in the literature. As a continuation of sentiment analysis, there are also studies on the emotion analysis. Due to the fact that many different emotions are needed to be dealt with at this point, the problem gets more complicated as the number of emotions to be detected increases. In this s...

Citation Formats

A. M. Ertugrul, I. Onal, and C. Acartürk, “Does the Strength of Sentiment Matter? A Regression Based Approach on Turkish Social Media,” 2017, vol. 10260, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/32610.