Exploiting social relations for sentiment analysis in microblogging

By Xia Hu, Lei Tang, Jiliang Tang, Huan Liu. Web Search and Data Mining, 2013

395 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/3d5a1904127679f50e1b3fdad77c342760e4b283

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

Detecting Emotional Contagion in Massive Social Networks (2014, methodology): “This problem has been addressed by using experimental methods to estimate network effects [17,18,19,20,21,22], but these methods are either limited in scale and external validity, or they require very close collaboration with private companies, which means there are limited opportunities to conduct ”
Sentiment analysis on evolving social streams: how self-report imbalances can help (2014, background): “The task of interpreting positive and negative feelings expressed on social streams exhibits a number of unique characteristics that are not present in the static and well-controlled domains on which sentiment analysis has focused in the last decade – mainly product and movie reviews [45, 37, 23].”
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory (2015, background): “While some other works utilize the microblogging features uncommon in the formal literature, such as hashtags, emoticons (Hu et al., 2013a; Liu et al., 2012).”
Exploiting Social Network Structure for Person-to-Person Sentiment Analysis (2014, background): “At right, the text compensates for edge-label sparsity. graph-cuts approach of Pang and Lee (2004) (2011) and Hu et al. (2013), who add terms to their models enforcing homophily between friends with regard to their preferences.”
Stylistic Variation in Social Media Part-of-Speech Tagging (2018, methodology): “Tan et al. (2011) and Hu et al. (2013) leverage social relations for sentiment analysis by exploiting a factor graph model and the graph Laplacian technique respectively, so that the tweets belonging to social connected users share similar label distributions.”
Label Informed Attributed Network Embedding (2017, background): “In addition, a number of data mining applications, such as sentiment analysis [12] and trust prediction [34], have been beneﬁted by exploiting the correlations between geometrical structure and node attributes.”
Twitter Sentiment Analysis (2015, positive): “For instance, (Hu et al., 2013) investigated how social relations can help sentiment analysis by introducing a Sociological Approach to handling Noisy and short Texts (SANT), (Zhu et al., 2014) showed that the quality of sentiment clustering for Twitter can be improved by joint clustering of…”
Learning Semantic Representations of Users and Products for Document Level Sentiment Classification (2015, methodology): “(2011) and Hu et al. (2013) utilize usertext and user-user relations for Twitter sentiment analysis.”
On Stopwords, Filtering and Data Sparsity for Sentiment Analysis of Twitter (2014, background): “…et al., 2012; Kouloumpis et al., 2011; Asiaee T et al., 2012) others claim that stopwords indeed carry sentiment information and removing them harms the performance of Twitter sentiment classifiers (Saif et al., 2012b; Hu et al., 2013b; Martınez-Cámara et al., 2013; Hu et al., 2013a).”
Distantly Supervised Lifelong Learning for Large-Scale Social Media Sentiment Analysis (2017, background): “Furthermore, some information specific in social media, such as emoticons and rich text information [7], [9], user relationship [12], social media text normalization [13], [14], and feature selection [15] was also incorporated for text representation.”
Accelerated Attributed Network Embedding (2017, background): “It becomes increasingly promising to advance the learning performance by jointly exploiting geometrical structures and node attributes [13, 21, 33].”
A Survey of Signed Network Mining in Social Media (2015, background): “We focus on these tasks because these these problems are very general and have applicability to many problems such as sentiment analysis [Tan et al. 2011; Hu et al. 2013].”
Unsupervised sentiment analysis with emotional signals (2013, result): “Similar to conventional sentiment analysis on product and movie reviews, most existing methods in social media can fall into supervised learning methods [10, 15] and unsupervised learning methods [4, 18, 24].”
Evaluation Datasets for Twitter Sentiment Analysis: A survey and a new dataset, the STS-Gold (2013, methodology): “The OMD dataset is a popular dataset, which has been used to evaluate various supervised learning methods [10,23,21], as well as unsupervised methods [9] for polarity classification of tweets.”
Like It or Not (2016, methodology): “This dataset has been used by many researchers for TSA [Hu et al. 2013a, 2013b; Saif et al. 2012b; Speriosu et al. 2011].”