Mind Your Language: Abuse and Offense Detection for Code-Switched Languages

Kapoor, Raghav; Kumar, Yaman; Rajput, Kshitij; Shah, Rajiv Ratn; Kumaraguru, Ponnurangam; Zimmermann, Roger

doi:10.48550/arxiv.1809.08652

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polyglot embeddings to mine conflict-specific slurs. We found frequent use of porkistan (an intra-word codemixed insult for Pakistan [14]) and randia (a code-mixed derogatory term for India). In order to uncover similar insults, we started with a seed set {porkistan, randia} and expanded it by including the top-ten nearest neighbors in the polyglot embedding space (distance metric: cosine similarity).…”

Section: Methodsmentioning

confidence: 92%

“…We manually annotated them and uncovered 243 insults 12 . Our hate lexicon mainly uncovered India-Pakistan specific insults and thus had minimal overlap with previously published hate lexicons [15,14].…”

Section: Methodsmentioning

confidence: 98%

“…280 users posted both types of comments. The Jaccard index 14 between the two user sets was 0.02 indicating low overlap.…”

Section: Temporal Trends In Pro-peace Intentmentioning

confidence: 99%

See 2 more Smart Citations

Hope Speech Detection: A Computational Analysis of the Voice of Peace

Palakodety¹,

KhudaBukhsh²,

Carbonell³

2019

Preprint

View full text Add to dashboard Cite

The recent Pulwama terror attack (February 14, 2019, Pulwama, Kashmir) triggered a chain of escalating events between India and Pakistan adding another episode to their 70-year-old dispute over Kashmir. The present era of ubiquitious social media has never seen nuclear powers closer to war.In this paper, we analyze this evolving international crisis via a substantial corpus constructed using comments on YouTube videos (921,235 English comments posted by 392,460 users out of 2.04 million overall comments by 791,289 users on 2,890 videos). Our main contributions in the paper are three-fold. First, we present an observation that polyglot word-embeddings reveal precise and accurate language clusters, and subsequently construct a document language-identification technique with negligible annotation requirements. We demonstrate the viability and utility across a variety of data sets involving several low-resource languages. Second, we present an extensive analysis on temporal trends of pro-peace and pro-war intent through a manually constructed polarity phrase lexicon. We observe that when tensions between the two nations were at their peak, pro-peace intent in the corpus was at its highest point. Finally, in the context of heated discussions in a politically tense situation where two nations are at the brink of a full-fledged war, we argue the importance of automatic identification of user-generated web content that can diffuse hostility and address this prediction task, dubbed hope-speech detection.

show abstract

Section: Methodsmentioning

confidence: 92%

Section: Methodsmentioning

confidence: 98%

See 1 more Smart Citation

Hope Speech Detection: A Computational Analysis of the Voice of Peace

Palakodety¹,

KhudaBukhsh²,

Carbonell³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of the previous efforts in the direction of understanding online opinions and reactions have been limited to developing methods for areas like sentiment analysis and opinion mining (Medhat et al, 2014;Baghel et al, 2018;Kapoor et al, 2018;Mahata et al, 2018a,b;Jangid et al, 2018;Meghawat et al, 2018;Shah and Zimmermann, 2017). Mining and understanding suggestions can open new areas to study consumer behavior and tapping nuggets of information that could be directly linked with the development and enhancement of products (Brun and Hagege, 2013;Dong et al, 2013;Ramanand et al, 2010), improve customer experiences (Negi and Buitelaar, 2015), and aid in understanding the linguistic nuances of giving advice (Wicaksono and Myaeng, 2013).…”

Section: Introductionmentioning

confidence: 99%

MIDAS at SemEval-2019 Task 9: Suggestion Mining from Online Reviews using ULMFit

Anand¹,

Mahata²,

Aggarwal³

et al. 2019

Proceedings of the 13th International Workshop on Semantic Evaluation

Self Cite

View full text Add to dashboard Cite

In this paper we present our approach and the system description for Sub Task A of SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. Given a sentence, the task asks to predict whether the sentence consists of a suggestion or not. Our model is based on Universal Language Model Finetuning for Text Classification. We apply various pre-processing techniques before training the language and the classification model. We further provide detailed analysis of the results obtained using the trained model. Our team ranked 10th out of 34 participants, achieving an F1 score of 0.7011. We publicly share our implementation 1 .

show abstract