Human interests, preferences and needs evolve over time. They change to reflect a growth in knowledge, the emergence of new interests and the waning of old. They are affected by context, both personal and global, be it the latest Olympic Games or your plans for the next Christmas holidays. They impact the way we look for and consume information. During my EDGE fellowship, I analysed the factors behind the temporal dynamics that govern information behaviour i.e. the time-based patterns and trends that reveal changes in the way humans interact with, seek, and utilise information. The TAPIR project defined a new generation of temporal-aware user models that support users in the seeking and consuming information, with the aim of providing the right information at the right moment.

Talks

[29/12/2019] “ADAPT centre podcast” [podcast]

[02/10/2018] “Forward to the Past” at Predict2018 [presentation] [video] [interview]

[29/06/2018] “Temporal Entity Random Indexing” at DH2018 [presentation]

In this exploratory research, we sought to investigate how we might identify and quantify the contextual shift surrounding significant entities in news based corpora. For example, might we be able to see changing public opinion such as that experienced by George W. Bush Jr. after the events of 9/11 and thus note how a population can rally behind their leader in the face of cultural trauma? Our method of identifying these changes has its roots in the field of distributional semantics and the measurement of semantic shift.

[29/05/2017] “Diachronic Analysis of Language exploiting Google Ngram” at MLDublin meets @Zalando [presentation] [video]

The diachronic analysis of language studies the language evolution over time. In this talk, I will introduce some methods for the diachronic analysis that rely on Distributional Semantic Models built over Google Ngram. I will show some preliminary results obtained for the Italian language and future work and challenges of this kind of analysis.

Publications

2019

  1. Kerin, B., Caputo, A., Lawless, S., 2019. Temporal Word Embeddings for Dynamic User Profiling in Twitter, in: Curry, E., Keane, M.T., Ojo, A., Salwala, D. (Eds.), Proceedings for the 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science, Galway, Ireland, December 5-6, 2019, CEUR Workshop Proceedings. CEUR-WS.org, pp. 470–479. [url]
  2. Basile, P., Semeraro, G., Caputo, A., 2019. Kronos-it: a Dataset for the Italian Semantic Change Detection Task, in: CLiC-It, CEUR Workshop Proceedings. CEUR-WS.org.
  3. Rossiello, G., Caputo, A., Basile, P., Semeraro, G., 2019. Modeling concepts and their relationships for corpus-based query auto-completion. Open Computer Science 9, 212–225. https://doi.org/10.1515/comp-2019-0015 [url]
  4. Chakraborty, A., Ganguly, D., Caputo, A., Lawless, S., 2019. A Factored Relevance Model for Contextual Point-of-Interest Recommendation, in: Proceedings of the 2019 ACM SIGIR International Conference On Theory of Information Retrieval, ICTIR 2019, Santa Clara, CA, USA, October 2-5, 2019. ACM, pp. 157–164.
  5. Basile, P., Caputo, A., Lawless, S., Semeraro, G., 2019. Diachronic Analysis of Entities by Exploiting Wikipedia Page Revisions, in: Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2019. INCOMA Ltd., Varna, Bulgaria, pp. 84–91.
  6. Bayomi, M., Caputo, A., Nicholson, M., Chakraborty, A., Lawless, S., 2019. CoRE: A Cold-start Resistant and Extensible Recommender System, in: Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, SAC ’19. ACM, New York, NY, USA, pp. 1679–1682. https://doi.org/10.1145/3297280.3297601 [url]

2018

  1. Caputo, A., Munnelly, G., Lawless, S., 2018. Temporal Entity Random Indexing, in: Palau, J.G., Russell, I.G. (Eds.), Digital Humanities 2018, DH 2018, Book of Abstracts, El Colegio De México, UNAM, and RedHD, Mexico City, Mexico, June 26-29, 2018. Red de Humanidades Digitales A. C., pp. 460–461. [pdf] [url] [presentation]
  2. Basile, P., Caputo, A., Semeraro, G., 2018. TRI: a tool for the diachronic analysis of large corpora and social media, in: Settimo Convegno Annuale AIUCD 2018, Bari, 31 January 31-2 February, 2018. pp. 222–227. [pdf]