Abusive Language Detection in Online User Content

Nobata, Chikashi; Tetreault, Joel; Thomas, Alexander S.; Mehdad, Yashar; Chang, Yi

doi:10.1145/2872427.2883062

Cited by 853 publications

(804 citation statements)

References 18 publications

Supporting

Mentioning

781

Contrasting

Unclassified

Order By: Relevance

“…The top performing baseline and current state-of-the-art, Nobata et al (2016), which consists of a comprehensive combination of a range of different features, is bested by NBSVM using solely character n-grams (77 F- For both NBSVM and RNNLM methods, character n-grams outperform their token counterparts (7 and 3 points F-1 score respectively). As most prior work has made use of blacklists and word ngrams, this proves to be an effective method for improving performance.…”

Section: Resultsmentioning

confidence: 99%

“…The top performing baseline and current state-of-the-art, Nobata et al (2016), which consists of a comprehensive combination of a range of different features, is bested by NBSVM using solely character n-grams (77 F- Table 1) outperforms all other methods in all measures save for recall. This shows that by increasing the number of relevant features we can improve precision with just a small loss in recall.…”

Section: Resultsmentioning

confidence: 99%

“…We use the same dataset employed in Djuric et al (2015b) and Nobata et al (2016). The labels came from a combination of in-house raters, users reactively flagging bad comments and abusive language pattern detectors.…”

Section: Methodsmentioning

confidence: 99%

“…Djuric et al (2015b) use a paragraph2vec approach to classify language on user comments as abusive or clean. Nobata et al (2016) was the first to evaluate many of the above features on a common corpus and showed an improvement over Djuric et al (2015b). In this paper, we directly compare against the two works by using the same dataset.…”

Section: Related Workmentioning

confidence: 99%

“…Table 1 shows the results of all experiments. The four baselines (Djuric et al (2015), Nobata et al (2016), token n-grams and C2V) are listed in the first seven rows, and the NBVSM and RNNLM experiments are listed under the double line. We also show the results of a method which combines the token n-grams with the features from the best performing versions of the C2V, NBSVM and RNNLM classes, using our SVM classifier ("Combination").…”

mentioning

confidence: 99%

See 4 more Smart Citations

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

We extend special thanks to our Local co-Chairs, Ron Artstein and Alesia Gainer, and their team of student volunteers. We know SIGDIAL 2016 would not have been possible without Ron and Alesia, who invested so much effort in arranging the conference venue and accommodations, handling registration, making banquet arrangements, and handling numerous other preparations for the conference. The student volunteers for on-site assistance also deserve our appreciation.Ethan Selfridge, Sponsorships Chair, has earned our appreciation for recruiting and liaising with our conference sponsors, many of whom continue to contribute year after year. Sponsorships support valuable aspects of the program, such as the invited speakers and conference banquet. In recognition of this, we gratefully acknowledge the support of our sponsors: (Platinum level) Microsoft Research, Xerox and PARC, Intel, (Gold level) Facebook, (Silver level) Amazon Alexa, Interactions, Educational Testing Service, Honda Research Institute, and Yahoo!. At the same time, we thank Priscilla Rasmussen at the ACL for tirelessly handling the financial aspects of sponsorship for SIGDIAL 2016, and for securing our ISBN.iii We also thank the SIGdial board, especially officers Amanda Stent, Jason Williams and Kristiina Jokinen for their advice and support from beginning to end.Finally, we thank all the authors of the papers in this volume, and all the conference participants for making this stimulating event a valuable opportunity for growth in the research areas of discourse and dialogue. AbstractThis paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent QNetworks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state. IntroductionTask-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003). The SDS agent has to achieve some predefined targets (e.g. booking a flight) through natural language interaction with the users. The typical structure of a task-oriented dialog system is outlined in Figure 1 (Young, 2006). This pipeline consists of several independently-developed modules: natural language understanding (the NLU) maps the user utterances to some semantic representation. This information is further processed by the dialog state tracker (DST), which accumulates the input of the turn along with the dialog history. The DST outputs the current dialog state and the dialog policy selects the next system action based on the dialog state. Then natural language gene...

show abstract

Section: Resultsmentioning

confidence: 99%

“…The top performing baseline and current state-of-the-art, Nobata et al (2016), which consists of a comprehensive combination of a range of different features, is bested by NBSVM using solely character n-grams (77 F- Table 1) outperforms all other methods in all measures save for recall. This shows that by increasing the number of relevant features we can improve precision with just a small loss in recall.…”

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Katagiri

Nakano

Fernández

et al. 2016

View full text Add to dashboard Cite

show abstract

Hate Neologism in Election Context in India

Das,

Senapati

2024

Mathematical Modeling for Computer Applications

View full text Add to dashboard Cite

Positive and negative behavioral analysis in social networks

Squicciarini

Rajtmajer

Griffin

2017

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Use of online social networks has grown dramatically since the first Web 2.0 technologies were deployed in the early 2000s. Our ability to capture user data, in particular behavioral data has grown in concert with increased use of these social systems. In this study, we survey methods for modeling and analyzing online user behavior. We focus on negative behaviors (social spamming and cyberbullying) and mitigation techniques for these behaviors. We also provide information on the interplay between privacy and deception in social networks and conclude by looking at trending and cascading models in social media. WIREs Data Mining Knowl Discov 2017, 7:e1203. doi: 10.1002/widm.1203 This article is categorized under: Commercial, Legal, and Ethical Issues > Social Considerations

show abstract

Abusive Language Detection in Online User Content

Cited by 853 publications

References 18 publications

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Hate Neologism in Election Context in India

Positive and negative behavioral analysis in social networks

Contact Info

Product

Resources

About