Sentiment Knowledge Discovery in Twitter Streaming Data

Bifet, Albert; Frank, Eibe

doi:10.1007/978-3-642-16184-1_1

Cited by 413 publications

(249 citation statements)

References 19 publications

Supporting

Mentioning

237

Contrasting

Unclassified

Order By: Relevance

“…Looking into users as a group creates a more complete solution when combined with traditional sentiment analysis approaches. (Bifet and Frank 2010;Pak and Paroubek 2010;Wang et al 2011;Thelwall et al 2011;Wang et al 2013;Go et al 2009;Diakopoulos and Shamma 2010).…”

Section: Related Workmentioning

confidence: 99%

Hashtags and followers

Martín

Lavesson

Doroud

2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

We have conducted an analysis of data from 502,891 Twitter users and focused on investigating the potential correlation between hashtags and the increase of followers to determine whether the addition of hashtags to tweets produces new followers. We have designed an experiment with two groups of users: one tweeting with random hashtags and one tweeting without hashtags. The results showed that there is a correlation between hashtags and followers: on average, users tweeting with hashtags increased their followers by 2.88, while users tweeting without hashtags increased 0.88 followers. We present a simple, reproducible approach to extract and analyze Twitter user data for this and similar purposes.

show abstract

Section: Related Workmentioning

confidence: 99%

Hashtags and followers

Martín

Lavesson

Doroud

2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…Liu et al [28] concatenate tweets of the same class (polarity) in large documents, from which a language model is derived and then classify tweets through maximum likelihood estimation, using both supervised and unsupervised data for training; the role of unsupervised data is to deal with words that do not appear in the vocabulary that can be built from a small supervised dataset. In [7] three approaches to sentiment classification are compared: Multinomial Naïve Bayes (MNB), Hinge Loss with Stochastic Gradient Descent and Hoeffding Tree; the authors report that MNB outperforms the other Fig. 1 Examples of tweets with images from the SentiBank Twitter dataset [8].…”

Section: Previous Workmentioning

confidence: 99%

A multimodal feature learning approach for sentiment analysis of social network multimedia

Baecchi

Uricchio

Bertini

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we investigate the use of a multimodal feature learning approach, using neural network based models such as Skip-gram and Denoising Autoencoders, to address sentiment analysis of micro-blogging content, such as Twitter short messages, that are composed by a short text and, possibly, an image. The approach used in this work is motivated by the recent advances in: i) training language models based on neural networks that have proved to be extremely efficient when dealing with web-scale text corpora, and have shown very good performances when dealing with syntactic and semantic word similarities; ii) unsupervised learning, with neural networks, of robust visual features, that are recoverable from partial observations that may be due to occlusions or noisy and heavily modified images. We propose a novel architecture that incorporates these neural networks, testing it on several standard Twitter datasets, and showing that the approach is efficient and obtains good classification results.

show abstract

“…Supervised approaches are based on training classifiers from various combinations of features such as word n-grams [15,5], Part-Of-Speech (POS) tags [4,1], and tweets syntax features (e.g., hashtags, retweets, punctuations, etc.) [12].…”

Section: Related Workmentioning

confidence: 99%

“…The smaller the x value, the stronger the sentiment. 5 Moreover, a small region called the "Neutral Region" can be defined. This region, as shown in Figure 1, is located very close to X-axis in the "Positive" and the "Negative" quadrants only, where terms lie in this region have very weak sentiment (i.e., |θ| ≈ 0).…”

Section: Representing Semantics With Senticirclesmentioning

confidence: 99%

SentiCircles for Contextual and Conceptual Semantic Sentiment Analysis of Twitter

Saif

Fernández

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Lexicon-based approaches to Twitter sentiment analysis are gaining much popularity due to their simplicity, domain independence, and relatively good performance. These approaches rely on sentiment lexicons, where a collection of words are marked with fixed sentiment polarities. However, words' sentiment orientation (positive, neural, negative) and/or sentiment strengths could change depending on context and targeted entities. In this paper we present SentiCircle; a novel lexicon-based approach that takes into account the contextual and conceptual semantics of words when calculating their sentiment orientation and strength in Twitter. We evaluate our approach on three Twitter datasets using three different sentiment lexicons. Results show that our approach significantly outperforms two lexicon baselines. Results are competitive but inconclusive when comparing to state-of-art SentiStrength, and vary from one dataset to another. SentiCircle outperforms SentiStrength in accuracy on average, but falls marginally behind in F-measure.

show abstract

Sentiment Knowledge Discovery in Twitter Streaming Data

Cited by 413 publications

References 19 publications

Hashtags and followers

Hashtags and followers

A multimodal feature learning approach for sentiment analysis of social network multimedia

SentiCircles for Contextual and Conceptual Semantic Sentiment Analysis of Twitter

Contact Info

Product

Resources

About