The italian music superdiversity

Geography, emotion and language: one resource to find them, one resource to rule them all


Globalization can lead to a growing standardization of musical contents. Using a cross-service multi-level dataset we investigate the actual Italian music scene. The investigation highlights the musical Italian superdiversity both individually analyzing the geographical and lexical dimensions and combining them. Using different kinds of features over the geographical dimension leads to two similar, comparable and coherent results, confirming the strong and essential correlation between melodies and lyrics. The profiles identified are markedly distinct one from another with respect to sentiment, lexicon, and melodic features. Through a novel application of a sentiment spreading algorithm and songs’ melodic features, we are able to highlight discriminant characteristics that violate the standard regional political boundaries, reconfiguring them following the actual musical communicative practices.

This is a preview of subscription content, access via your institution.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11


  1. 1.

    All Music Guide website:

  2. 2.

    The Amazon Mechanical Turk (MTurk) is a web server for works that require human intelligence. Developers can exploit the service to build human intelligence directly into their applications.

  3. 3. website:

  4. 4.

    Discogs website:

  5. 5.

    AIDAinformazioni, Anno 34, numero 1-2, 2016:

  6. 6.

    2007 Audio Music Mood Classification:

  7. 7.

    The service is now inactive, with the URL resulting in a 404 response.

  8. 8.

    The two version of the WDYL’s list can be public downloaded from

  9. 9.

    Googletrans is a free and unlimited python library that implemented Google Translate API. For more details see

  10. 10.

    Goslate provides a python API to Google translation service by querying google translation website. More details can be found at

  11. 11.

    “Crooner” is an American term given to male singers of jazz standards, accompanied by either a full orchestra, a big band or a piano. The most famous America crooner is Frank Sinatra, despite the fact that he does not consider himself a crooner.

  12. 12.

    For example, the dictionary we obtained for Lazio for a selected run with best parameters (the same showed in Fig. 9a) is composed of 11,243 Italian lemmas, each labeled with a polarity score in the range [0,10].


  1. 1.

    Bischoff K, Firan CS, Paiu R, Nejdl W, Laurier C, Sordo M (2009) Music mood and theme classification-a hybrid approach. In: ISMIR, pp 657–662

  2. 2.

    Bradley MM, Lang PJ (1999) Affective norms for english words (anew): instruction manual and affective ratings. Tech. rep., Citeseer

  3. 3.

    Çano E., Morisio M (2017) Moodylyrics: a sentiment annotated lyrics dataset. In: Proceedings of the 2017 international conference on intelligent systems, metaheuristics & swarm intelligence. ACM, pp 118–124

  4. 4.

    Çano E., Morisio M (2017) Music mood dataset creation based on last fm tags

  5. 5.

    Celma O (2010) Music recommendation. In: Music recommendation and discovery. Springer, pp 43–85

  6. 6.

    Dodds P S, Danforth C M (2010) Measuring the happiness of large-scale written expression: songs, blogs, and presidents. J Happiness Stud 11(4):441–456

    Article  Google Scholar 

  7. 7.

    Downie X, Laurier C, Ehmann M (2008) The 2007 mirex audio mood classification task: Lessons learned. In: Proceedings 9th int. Conf. Music inf. retrieval, pp 462–467

  8. 8.

    Echonest web api (2018).

  9. 9.

    Esuli A, Sebastiani F (2007) Sentiwordnet: a high-coverage lexical resource for opinion mining. Evaluation, pp 1–26

  10. 10.

    Guerini M, Gatti L, Turchi M (2013) Sentiment analysis: how to derive prior polarities from sentiwordnet. arXiv:1309.5843

  11. 11.

    Google form service (2018).

  12. 12.

    Helmholz P, Siemon D, Robra-Bissantz S Summer hot, winter not!–seasonal influences on context-based music recommendations

  13. 13.

    Hu X, Downie JS (2007) Exploring mood metadata: relationships with genre, artist and usage metadata. In: ISMIR, pp 67–72

  14. 14.

    Hu X, Downie JS (2010) When lyrics outperform audio for music mood classification: a feature analysis. In: ISMIR, pp 619–624

  15. 15.

    Hu X, Downie JS, Ehmann AF (2009) Lyric text mining in music mood classification. Am Music 183(5,049):2–209

    Google Scholar 

  16. 16.

    Lamere P, Pampalk E, Schmitz C, Bello J, Chew E, Turnbull D (2008) Social tags and music information retrieval. In: ISMIR, p 24

  17. 17.

    Laurier C, Sordo M, Serra J, Herrera P (2009) Music mood representations from social tags. In: ISMIR, pp 381–386

  18. 18.

    Lee JH, Hu X (2012) Generating ground truth for music mood classification using mechanical turk. In: Proceedings of the 12th ACM/IEEE-CS joint conference on digital libraries. ACM, pp 129–138

  19. 19.

    Li T, Ogihara M (2004) Music artist style identification by semi-supervised learning from both lyrics and content. In: Proceedings of the 12th annual ACM international conference on multimedia. ACM, pp 364–367

  20. 20.

    Lyding V, Stemle E, Borghetti C, Brunello M, Castagnoli S, Dell’Orletta F, Dittmann H, Lenci A, Pirrelli V (2014) The paisa’corpus of italian web texts. In: 9th web as corpus workshop (wac-9)@ EACL 2014, pp 36–43. EACL (European chapter of the association for computational linguistics)

  21. 21.

    Malheiro R, Panda R, Gomes P, Paiva R P (2016) Classification and regression of music lyrics: Emotionally-significant features. In: 8th international conference on knowledge discovery and information retrieval

  22. 22.

    Mihalcea R, Strapparava C (2012) Lyrics, music, and emotions. In: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning. Association for Computational Linguistics, pp 590–599

  23. 23.

    Perna S, Guarasci R, Maisto A, Vitale P (2016) Il linguaggio del rap. possibilità di un’analisi multidisciplinare. In: Editrice A. (ed) XXVI Convegno internazionale ass.i.term. Terminologia e organizzazione della conoscenza nella conservazione della memoria digitale, vol 34. AIDAinformazioni, Rende (CS), pp 209–217

  24. 24.

    PODIUC RE, GRATIE D, VOICU O Inferring song moods from lyrics

  25. 25.

    Pollacci L, Guidotti R, Rossetti G (2016) Are we playing like music-stars? Placing emerging artists on the Italian music scene. In: 9th international workshop on machine learning and music

  26. 26.

    Pollacci L, Guidotti R, Rossetti G, Giannotti F, Pedreschi D (2017) The fractal dimension of music: geography, popularity and sentiment analysis. In: International conference on smart objects and technologies for social good, pp 183–194. Springer

  27. 27.

    Pollacci L, Sîrbu A, Giannotti F, Pedreschi D, Lucchese C, Muntean CI (2017) Sentiment spreading: an epidemic model for lexicon-based sentiment analysis on twitter. In: Conference of the Italian association for artificial intelligence. Springer, pp 114–127

  28. 28.

    Rawlings D, Ciancarelli V (1997) Music preference and the five-factor model of the neo personality inventory. Psychol Music 25(2):120–132

    Article  Google Scholar 

  29. 29.

    Rentfrow PJ, Gosling SD (2003) The do re mi’s of everyday life: the structure and personality correlates of music preferences. J Pers Soc Psychol 84(6):1236

    Article  Google Scholar 

  30. 30.

    Russell JA (1980) A circumplex model of affect. J Pers Soc Psychol 39(6):1161

    Article  Google Scholar 

  31. 31.

    Schedl M, Orio N, Liem C, Peeters G (2013) A professionally annotated and enriched multimodal data set on popular music. In: Proceedings of the 4th ACM multimedia systems conference. ACM, pp 78–83

  32. 32.

    Schmid H (1995) Improvements in part-of-speech tagging with an application to German. In: Proceedings of the acl sigdat-workshop. Citeseer

  33. 33.

    Schmid H (2013) Probabilistic part-ofispeech tagging using decision trees. In: New methods in language processing, p 154

  34. 34.

    Soundcloud web api (2018).

  35. 35.

    Spotify (2018).

  36. 36.

    Spotify web api (2018).

  37. 37.

    Toscana100band contest (2018).

  38. 38.

    Trohidis K, Tsoumakas G, Kalliris G, Vlahavas IP (2008) Multi-label classification of music into emotions. In: ISMIR, vol 8, pp 325–330

  39. 39.

    Turnbull D, Barrington L, Torres D, Lanckriet G (2008) Semantic annotation and retrieval of music and sound effects. IEEE Trans Audio Speech Lang Process 16(2):467–476

    Article  Google Scholar 

  40. 40.

    Vertovec S (2006) The emergence of super-diversity in Britain. Centre of Migration, Policy and Society University of Oxford

  41. 41.

    Vertovec S (2007) Super-diversity and its implications. Ethn Racial Stud 30(6):1024–1054

    Article  Google Scholar 

  42. 42.

    Wikipedia - ita version (2018).

Download references


This work is supported by the European Community’s H2020 Program under the funding scheme “INFRAIA-1-2014-2015: Research Infrastructures” grant agreement,, GS501100001809, 654024 “SoBigData: Social Mining & Big Data Ecosystem”.

Author information



Corresponding author

Correspondence to Laura Pollacci.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Pollacci, L., Guidotti, R., Rossetti, G. et al. The italian music superdiversity. Multimed Tools Appl 78, 3297–3319 (2019).

Download citation


  • Music data analytics
  • Sentiment pattern discovery
  • Music sentiment analytics
  • Multi-source analytics
  • Music sentiment analysis
  • Superdiversity