What We Can Learn from Looking at Profanity

Laboreiro, Gustavo; Oliveira, Eugénio C.

doi:10.1007/978-3-319-09761-9_11

Cited by 11 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We do note that there are many different types of online communities, and that in communities with little to no moderation, character and word n-grams may perform similarly since the writers may not feel it necessary to obfuscate their words. However, in the many communities where authors are aware of standards, the task becomes much more challenging as authors intentional obfuscate in a myriad of creative ways (Laboreiro and Oliveira, 2014).…”

Section: Resultsmentioning

confidence: 99%

Do Characters Abuse More Than Words?

Mehdad¹,

Tetreault²

2016

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

138

View full text Add to dashboard Cite

Although word and character n-grams have been used as features in different NLP applications, no systematic comparison or analysis has shown the power of character-based features for detecting abusive language. In this study, we investigate the effectiveness of such features for abusive language detection in user-generated online comments, and show that such methods outperform previous state-of-theart approaches and other strong baselines.

show abstract

Section: Resultsmentioning

confidence: 99%

Do Characters Abuse More Than Words?

Mehdad¹,

Tetreault²

2016

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

138

View full text Add to dashboard Cite

show abstract

“…However, in the many communities where authors are aware of standards, the task becomes much more challenging as authors intentional obfuscate in a myriad of creative ways (Laboreiro and Oliveira, 2014).…”

Section: Resultsmentioning

confidence: 99%

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

“…We compute a set of features that measure how easy it is to read a text. These include vocabulary richness (i.e., how diverse the vocabulary used by an author is, in other words, the ratio of unique tokens), and ratios such as the percentage of long words (> 12 characters), obfuscated words [30] (words with numbers or special characters, e.g. "cr1me"), misspelled words, polysyllable words (> 2 syllables).…”

Section: Readabilitymentioning

confidence: 99%

Automated Fake News Detection Using Computational Forensic Linguistics

Moura

Sousa‐Silva

Cardoso

2021

Progress in Artificial Intelligence

View full text Add to dashboard Cite

In our society, almost everyone has access to the internet and can post anything about any topic at any time. Despite its many advantages, this possibility brought along a serious problem: fake news. Fake news can emerge very easily and rapidly spread mis-and disinformation across the world. As a result, the phenomenon has gained particular relevance over the past few decades. There is no consensual and objective vision of what fake news is, but in the context of this work, fake news is news that does not follow the journalism principles of factuality, objectivity, and neutrality. Instead, fake news try to mimic the look and feel of real news with the intent to disinform the reader.What makes fake news a real problem is its potential negative impact on our society. Lay people are attracted to this kind of news because of their appealing titles and often give more attention to them than to truthful accounts. Although fake news have always existed, their use as a form of manipulation and control has recently gained attention, due to their fast and immediate propagation, mainly through social media, without any kind of curation or filtering. Their influence is noticeable in recent events, such as the previous election of Trump (2016) in the USA or Bolsonaro in Brazil (2018), where, according to some sources, fake news was a key determinant of the outcome of the election.Despite the development of advanced computer systems to detect fake news, most are based on fact-checking methods. These methods are useful when facts are manipulated, but not so much when the truth in the news is distorted, exaggerated, or even placed out of context. In this work we address the fake news phenomenon by using an approach based on forensic linguistic analysis. Contrary to previous works on fake news detection, our approach builds upon methods of linguistic and stylistic analysis that have been explored in forensic linguistics. These include, but are not limited to: text statistics; spelling; n-grams; lexical choices; etc. A model built upon these features, which have been previously tested, e.g., to attribute authorship or detect bias in text, have a significant potential to detect fake news.The best results reported are very promising and comparable to the state-of-the-art NLP models (e.g., BERT and GPT-2), achieving an accuracy of 97% and a macro average f1-score of 91%. However, contrary to the state-of-the-art NLP models (most based on Deep Learning), our approach has the potential to reveal several insights into how the models discriminate fake and genuine news. Although comparing the results to those in the literature review is a non-trivial task due to different datasets used, we hope that this work will spark new investigation and operate as a baseline to future Portuguese fake news detection work.

show abstract

What We Can Learn from Looking at Profanity

Cited by 11 publications

References 6 publications

Do Characters Abuse More Than Words?

Do Characters Abuse More Than Words?

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

Automated Fake News Detection Using Computational Forensic Linguistics

Contact Info

Product

Resources

About