Skip to main content

Adam Tsakalidis

I am a PhD candidate (PhD in Urban Science), supervised by Alexandra I. Cristea and Maria Liakata. My main research interests are in the areas of Social Media Mining and Natural Language Processing, with a primary focus on sentiment and emotion mining from social media in a longitudinal fashion and their implications in real-world events.

I am originally from Thessaloniki, Greece. I have completed my undergraduate studies in the University of Thessaly (Greece) and my postgraduate (MSc) ones in the University of Warwick (UK), both in the rather broad field of Computer Science. I have done several internships and worked as a Research Assistant at the Information Technologies Institute during the SocialSensor project. Currently I am a member of WISC and IAS groups at the University of Warwick.

When spending time out of research, I am being awful at playing chess and a pretty bad guitar player.

PhD Research

The adoption of social media and smart devices by millions of users worldwide over the last decade has resulted in an unprecedented opportunity for NLP and social sciences. Users publish their thoughts and opinions on everyday issues through social media platforms, while they record their digital traces through their smart devices. Mining these rich resources offers new opportunities in sensing real-world events and indices (e.g., political preference, mental health indices) in a longitudinal fashion, either at the macro (population)-, or at the micro(user)-level.

My research aims at developing approaches to "nowcast" (predict the current state of) such indices at both levels of granularity. The basis of my work lies within the areas of natural language processing and machine learning: from (static) document-level analysis tasks (e.g., sentiment analysis) to longitudinal modelling of macro- or micro-level indices in a temporally sensitive manner, using heterogeneous and asynchronous data generated by social media and smart phone users. My primary application areas lie within the political and the mental health domains.

Keywords: natural language processing, machine learning, longitudinal modelling, social media, smartphones



  1. Tsakalidis, A., Aletras, N., Cristea, A.I. and Liakata, M., 2018. Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum. arXiv preprint arXiv:1808.08538 (accepted for publication in the 2018 ACM International Conference on Information and Knowledge Management – ACM CIKM).
  2. Tsakalidis, A., Liakata, M., Damoulas, T. and Cristea, A.I., 2018. Can We Assess Mental Health through Social Media and Smart Devices? Addressing Bias in Methodology and Evaluation. arXiv preprint arXiv:1807.07351 (accepted for publication in the 2018 European Conference on Machine Learning and European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases – ECMLPKDD/ADS).
  3. Tsakalidis, A., Liakata, M., Damoulas, T., Jellinek, B., Guo, W. and Cristea, A., 2016. Combining Heterogeneous User Generated Data to Sense Well-Being. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers (pp. 3007-3018).
  4. Tsakalidis, A., Papadopoulos, S. and Kompatsiaris, I., 2014, October. An Ensemble Model for Cross-Domain Polarity Classification on Twitter. In International Conference on Web Information Systems Engineering (pp. 168-177). Springer, Cham. 
  1. Tsakalidis, A., Papadopoulos, S., Voskaki, R., Ioannidou, K., Boididou, C., Cristea, A.I., Liakata, M. and Kompatsiaris, Y., 2018. Building and Evaluating Resources for Sentiment Analysis in the Greek Language. Language Resources and Evaluation, pp.1-24.
  2. Zubiaga, A., Voss, A., Procter, R., Liakata, M., Wang, B. and Tsakalidis, A., 2017. Towards Real-Time, Country-Level Location Classification of Worldwide Tweets. IEEE Transactions on Knowledge and Data Engineering, 29(9), pp.2053-2066.
  3. Tsakalidis, A., Papadopoulos, S., Cristea, A.I. and Kompatsiaris, Y., 2015. Predicting Elections for Multiple Countries Using Twitter and Polls. IEEE Intelligent Systems, 30(2), pp.10-17.
  1. Wang, B., Liakata, M., Tsakalidis, A., Kolaitis, S.G., Papadopoulos, S., Apostolidis, L., Zubiaga, A., Procter, R. and Kompatsiaris, Y., 2017. TOTEMSS: Topic-Based, Temporal Sentiment Summarisation for Twitter. Proceedings of the IJCNLP 2017, System Demonstrations, pp.21-24. 
  2. Townsend, R., Tsakalidis, A., Zhou, Y., Wang, B., Liakata, M., Zubiaga, A., Cristea, A. and Procter, R., 2015. WarwickDCS: From Phrase-Based to Target-Specific Sentiment Recognition. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015) (pp. 657-663).

Resources and Datasets

Greek Sentiment/Emotion Lexicon (manually annotated)

Resources for Sentiment-Related Tasks in Social Media in the Greek Language (datasets, lexicons, embeddings)

Other Links

UK 2015 Election Study on Twitter

Can we predict our political future?

Predicting the EU 2014 Election Results for Greece using Twitter

Adam Tsakalidis Profile

Adam Tsakalidis

A dot Tsakalidis at warwick dot ac dot uk