Towards Target-Dependent Sentiment Classification in News Articles

Extensive research on target-dependent sentiment classification (TSC) has led to strong classification performances in domains where authors tend to explicitly express sentiment about specific entities or topics, such as in reviews or on social media. We investigate TSC in news articles, a much less researched domain, despite the importance of news as an essential information source in individual and societal decision making. This article introduces NewsTSC, a manually annotated dataset to explore TSC on news articles. Investigating characteristics of sentiment in news and contrasting them to popular TSC domains, we find that sentiment in the news is expressed less explicitly, is more dependent on context and readership, and requires a greater degree of interpretation. In an extensive evaluation, we find that the current state-of-the-art in TSC performs worse on news articles than on other domains (average recall AvgRec = 69.8 on NewsTSC compared to AvgRev = [75.6, 82.2] on established TSC datasets). Reasons include incorrectly resolved relation of target and sentiment-bearing phrases and off-context dependence. As a major improvement over previous news TSC, we find that BERT’s natural language understanding capabilities capture the less explicit sentiment used in news articles.

[1]  Suresh Manandhar,et al.  SemEval-2015 Task 12: Aspect Based Sentiment Analysis , 2015, *SEMEVAL.

[2]  Sebastian Stabinger,et al.  Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification , 2020, LREC.

[3]  Tao Jiang,et al.  Targeted Sentiment Classification with Attentional Encoder Network , 2019, ICANN.

[4]  Thomas Wolf,et al.  DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.

[5]  A. Feinstein,et al.  High agreement but low kappa: II. Resolving the paradoxes. , 1990, Journal of clinical epidemiology.

[6]  Felix Hamborg,et al.  The POLUSA Dataset: 0.9M Political News Articles Balanced by Time and Outlet Popularity , 2020, JCDL.

[7]  Preslav Nakov,et al.  SemEval-2016 Task 4: Sentiment Analysis in Twitter , 2016, *SEMEVAL.

[8]  Pinlong Zhaoa,et al.  Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification , 2019, Knowl. Based Syst..

[9]  Bela Gipp,et al.  Automated Identification of Media Bias by Word Choice and Labeling in News Articles , 2019, 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL).

[10]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[11]  Mattias Polborn,et al.  Political Polarization and the Electoral Effects of Media Bias , 2006, SSRN Electronic Journal.

[12]  Saif Mohammad,et al.  NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews , 2014, *SEMEVAL.

[13]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[14]  Norman Meuschke,et al.  news-please - A Generic News Crawler and Extractor , 2017, ISI.

[15]  Bruno Pouliquen,et al.  Sentiment Analysis in the News , 2010, LREC.

[16]  Felix Hamborg,et al.  Media Bias, the Social Sciences, and NLP: Automating Frame Analyses to Identify Bias by Word Choice and Labeling , 2020, ACL.

[17]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[18]  M. Baum,et al.  Barbarians Inside the Gates: Partisan New Media and the Polarization of American Political Discourse , 2007 .

[19]  Bela Gipp,et al.  Newsalyze: Enabling News Consumers to Understand Media Bias , 2020, JCDL.

[20]  Margrit Schreier,et al.  Qualitative Content Analysis in Practice , 2012 .

[21]  D. S. Buck,et al.  HOUSTON , 2021, Resilient City.

[22]  Bela Gipp,et al.  Enabling News Consumers to View and Understand Biased News Coverage: A Study on the Perception and Visualization of Media Bias , 2020, JCDL.

[23]  Tim Groseclose,et al.  A Measure of Media Bias , 2005 .

[24]  Preslav Nakov,et al.  SemEval-2013 Task 2: Sentiment Analysis in Twitter , 2013, *SEMEVAL.

[25]  Justin M. Rao,et al.  Fair and Balanced? Quantifying Media Bias through Crowdsourced Content Analysis , 2016 .

[26]  Heng Yang,et al.  LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification , 2019, Applied Sciences.

[27]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[28]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Ming Zhou,et al.  Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification , 2014, ACL.

[30]  Bela Gipp,et al.  Automated identification of media bias in news articles: an interdisciplinary literature review , 2018, International Journal on Digital Libraries.

[31]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[32]  Derek Greene,et al.  Practical solutions to the problem of diagonal dominance in kernel document clustering , 2006, ICML.

[33]  Steven Skiena,et al.  Large-Scale Sentiment Analysis for News and Blogs (system demonstration) , 2007, ICWSM.

[34]  Ralf Steinberger,et al.  Large-scale news entity sentiment analysis , 2017, RANLP.

[35]  Tiejun Zhao,et al.  Target-dependent Twitter Sentiment Classification , 2011, ACL.