A Computational Analysis of the Language of Drug Addiction

Strapparava, Carlo; Mihalcea, Rada

doi:10.18653/v1/e17-2022

Cited by 4 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is, not only the written verses but also music sheets. The parallel corpus from Strapparava et al (2012), which includes annotations on the notes and lyrics of popular music in English, can be leveraged to investigate the cooperation between textual features and musical features for emotion identification (Mihalcea and Strapparava 2012). In the case of operas, even scene representations could be taken into consideration in the decision process.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias

Zhang¹,

Fernicola²,

Garcea³

et al. 2022

ijcol

View full text Add to dashboard Cite

We present the task of identifying the emotions conveyed by the lyrics of Italian opera arias. We shape the task as a multi-class supervised problem, considering the six emotions from Parrot's tree: love, joy, admiration, anger, sadness, and fear. We manually annotated an opera corpus with 2.5k instances at the verse level and experimented with different classification models and representations to identify the expressed emotions. Our best-performing models consider character 3-gram representations and reach relatively low levels of macro-averaged F 1 . Such performance reflects the difficulty of the task at hand, partially caused by the size and nature of the corpus: relatively short verses written in 18th-century Italian. Building on what we learned from the verse-level setting, we adopt a higher granularity and increase the size of the corpus. First, we switch from verses to arias in order to have longer and more expressive texts. Second, we construct a new corpus with 40k arias (∼ 90k verses). This new dataset contains silver data, annotated by self-learning on the basis of an ensemble of binary classifiers.We then experiment with more sophisticated representations, by learning an embedding space and using it to train new models for the identification of emotions at the aria level, obtaining a significant performance boost.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Both MultiEmotion-It and FEEL-IT contain annotations at the document level (be it a tweet or a comment). As Strapparava et al (2012), who released a corpus of popular music in English, we go at the sub-document level and annotate single verses and arias.…”

Section: Related Workmentioning

confidence: 99%

AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias

Zhang¹,

Fernicola²,

Garcea³

et al. 2022

ijcol

View full text Add to dashboard Cite

show abstract

“…It has several attractive properties: its emotion word categories and the associated word lists have been validated through human evaluation (Tausczik and Pennebaker 2010), LIWC can be used with arbitrary datasets and requires no preprocessing of the input texts. As a result, LIWC has been used in a large number of psychological studies (Cohn et al 2004;Pennebaker and Graybeal 2001;Rude et al 2004;Stirman and Pennebaker 2001) and NLP studies (e.g., Mihalcea and Strapparava 2009;Nguyen et al 2011;Strapparava and Mihalcea 2017). For example, in a study on language and depression, Rude et al (2004) analyzed the language of depressed, formerly-depressed, and never-depressed students and found that, as one would expect, depressed participants used more negatively valenced words, but also, perhaps less expected, used the pronoun ''I'' more frequently than never-and formerly-depressed students.…”

Section: The Psychology Of Language and Emotionmentioning

confidence: 99%

MEmoFC: introducing the Multilingual Emotional Football Corpus

Braun

Lee

Gatti

et al. 2020

Lang Resources & Evaluation

View full text Add to dashboard Cite

This paper introduces a new corpus of paired football match reports, the Multilingual Emotional Football Corpus, (MEmoFC), which has been manually collected from English, German, and Dutch websites of individual football clubs to investigate the way different emotional states (e.g. happiness for winning and disappointment for losing) are realized in written language. In addition to the reports, it also contains the statistics for the selected matches. MEmoFC is a corpus consisting of comparable subcorpora since the authors of the texts report on the same event from two different perspectives—the winner’s and the loser’s side, and from an arguably more neutral perspective in tied matches. We demonstrate how the corpus can be used to investigate the influence of affect on the reports through different approaches and illustrate how game outcome influences (1) references to the own team and the opponent, and (2) the use of positive and negative emotion terms in the different languages. The MEmoFC corpus, together with the analyzed aspects of emotional language will open up new approaches for targeted automatic generation of texts.

show abstract

Reading the Author and Speaker: Towards a Holistic and Deep Approach on Automatic Assessment of What is in One’s Words

Schuller

2018

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

A Computational Analysis of the Language of Drug Addiction

Cited by 4 publications

References 27 publications

AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias

AriEmozione 2.0: Identifying Emotions in Opera Verses and Arias

MEmoFC: introducing the Multilingual Emotional Football Corpus

Reading the Author and Speaker: Towards a Holistic and Deep Approach on Automatic Assessment of What is in One’s Words

Contact Info

Product

Resources

About