BibTeX

@inProceedings{kokkinakis-etal-2023-investigating-325628,
	title        = {Investigating the Effects of MWE Identification in Structural Topic Modelling
},
	abstract     = {Multiword expressions (MWEs) are common word combinations which exhibit idiosyncrasies in various linguistic levels. For various downstream natural language processing applications and tasks, the identification and discovery of MWEs has been proven to be potentially practical and useful, but still challenging to codify. In this paper we investigate various, relevant to MWE, resources and tools for Swedish, and, within a specific application scenario, we apply structural topic modelling to investigate whether there are any interpretative advantages of identifying MWEs.},
	booktitle    = {The 19th Workshop on Multiword Expressions (MWE 2023)},
	author       = {Kokkinakis, Dimitrios and Muñoz Sánchez, Ricardo and Bruinsma, Sebastianus C. J. and Hammarlin, Mia-Marie},
	year         = {2023},
	publisher    = {ACL},
	ISBN         = {978-1-959429-59-3},
}

@inProceedings{kokkinakis-etal-2023-scaling-326698,
	title        = {Scaling-up the Resources for a Freely Available Swedish VADER (svVADER)
},
	abstract     = {With widespread commercial applications in various domains, sentiment analysis has become a success story for Natural Language Processing (NLP). Still, although sentiment analysis has rapidly progressed during the last years, mainly due to the application of modern AI technologies, many approaches apply knowledge-based strategies, such as lexicon-based, to the task. This is particularly true for analyzing short social media content, e.g., tweets. Moreover, lexicon-based sentiment analysis approaches are usually preferred over learning-based methods when training data is unavailable or insufficient. Therefore, our main goal is to scale-up and apply a lexicon-based approach which can be used as a baseline to Swedish sentiment analysis. All scaled-up resources are made available, while the performance of this enhanced tool is evaluated on two short datasets, achieving adequate results.
},
	booktitle    = {Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)},
	author       = {Kokkinakis, Dimitrios and Muñoz Sánchez, Ricardo and Hammarlin, Mia-Marie},
	year         = {2023},
}

@misc{dunabeitia-etal-2023-editorial-333441,
	title        = {Editorial: Digital Linguistic Biomarkers: Beyond Paper and Pencil Tests -Volume II
},
	abstract     = {Our first volume laid the foundation for understanding the potential of digital linguistic biomarkers in assessing various cognitive and psychological aspects. In this second volume, we witness a significant advancement in both the scope and depth of research in this area. The featured articles in this volume contribute to our understanding of how linguistic biomarkers can transcend traditional paper-and-pencil tests, offering a more nuanced and comprehensive approach to the assessment of cognitive function and psychological well-being.In the first study of the volume [Gonzalez-Recober et al., 2023], the authors employed automated methods to investigate speech production during category and letter fluency tasks, commonly used neuropsychological assessments for evaluating lexical retrieval abilities. Their analysis encompassed a diverse range of linguistic and acoustic features, providing a more comprehensive perspective on these tasks than previous studies. As expected, participants produced more words during the category fluency task than during the letter fluency task. Moreover, several linguistic and acoustic measures displayed distinctions between the two tasks. The automated techniques employed in this study offer a reproducible and scalable approach for analyzing fluency tasks, with potential applications in clinical settings. By implementing these methods, future research endeavors are expected to expand our knowledge of speech feature differences, not only in terms of total scores but also across various speech measures, particularly among clinical populations.In the second article of the volume [Sánchez-Vincitore et al. 2023], the authors present a longitudinal analysis of linguistic biomarkers to detect cognitive decline. Their study underscores the potential of natural language processing techniques in identifying subtle cognitive changes over time. They examined data from over 3,000 participants aged 45 and older to investigate the relationship between age, gender, and language-mediated working memory processes using commercial cognitive tests (in their case, scientific tests developed by CogniFit Inc.). The findings revealed that age negatively predicted working memory performance, highlighting the potential of computerized assessments in predicting cognitive functions during aging and the need for further research on gender effects in cognitive aging. This study contributed to the growing body of evidence supporting the utility of linguistic biomarkers in early cognitive assessment.In the third study of our volume [Kim et al. 2023], the focus shifts to postoperative delirium (POD) in elderly patients following spinal surgery. POD has been linked to adverse outcomes in this demographic, prompting researchers to explore potential biomarkers for degenerative cerebral dysfunctions like mild cognitive impairment and dementia. The authors used electroencephalography (EEG) to measure an EEG biomarker reflecting idle cortical states through intrinsic alpha oscillations in the prefrontal regions. Cognitive follow-ups were performed using the Telephone Interview for Cognitive Status™ (TICS). The study observed that among patients diagnosed with POD, neurocognitive disorders could persist for up to 1 year postsurgery. These findings suggest that EEG has the potential to be a novel and valuable tool for identifying elderly surgical patients at a higher risk of developing postoperative delirium, offering opportunities for early intervention and improved patient outcomes.As the fourth article in our volume, the study by [Saccone et al. 2023] delves into the realm of schizophrenia, examining how it affects speech prosody and pragmatic functions. The study conducted corpus-based research, focusing on real-life spontaneous interactions to shed light on the prosodic features of schizophrenia. Notably, the speech patterns of patients revealed distinct characteristics. Their speech was organized into smaller, less structured information chunks, punctuated by frequent silences and extended pauses during turn-taking. Fluency was disrupted by retracing phenomena, particularly in complex information structures. Besides, comparing Topic and Comment-prominences between patients and non-pathological individuals revealed a consistent pattern. Patients exhibited higher values for Topic-prominence across all parameters, while the non-pathological group displayed the opposite trend. These findings provide valuable insights into the prosodic and pragmatic aspects of speech in schizophrenia, emphasizing the importance of understanding these linguistic manifestations in the context of the disorder's impact on communication.In closing, the second volume of "Digital Linguistic Biomarkers: Beyond Paper and Pencil Tests" presents a short yet diverse and comprehensive array of research articles that collectively advance the field. These contributions not only underscore the relevance and timeliness of linguistic biomarkers in the digital age but also highlight their potential to revolutionize the way we assess cognitive function, psychological well-being, and aging across diverse populations, extending to pathological and clinical samples.},
	author       = {Dunabeitia, Jon Andoni and Kokkinakis, Dimitrios and Gagliardi, Gloria},
	year         = {2023},
	volume       = {14},
}

@inProceedings{beccaria-etal-2023-extraction-334169,
	title        = {Extraction and Analysis of Acoustic Features from Italian-Speaking Children with Autism Spectrum Disorder
},
	abstract     = {Background: The persistent difficulties in social interaction and communication that characterize Autism Spectrum Disorder can be accessed by investigating the quality of language. Indeed, these deficits involve the presence of anomalies in speech production and understanding, which find an expression at the acoustic and prosodic levels of linguistic analysis.
Objectives: The main aim of this work is to propose a speech pipeline for the extraction of Italian speech biomarkers typical of ASD by conducting an acoustic and phonological analysis. Moreover, we will highlight the strengths and difficulties of this kind of investigation introducing new topics for further research.
Methods: The poster will present the analysis of a speech corpus of 14 Italian-speaking children with ASD and 14 controls (C). The corpus is demographically balanced (age 6-10, 8;1 ± 1;3. Sex: 3F, 11 M) and homogeneous at the diatopic level (origin: Prato, Pistoia, Florence).
First, we extracted the acoustic features by using eGeMAPS (openSMILE; Eyben et al., 2015), specifically ideated for the study of impaired speech. Then, we implemented the Mann-Whitney U-test to select the features with the most statistically significant distance in the production of the two groups.
Secondly, we conducted a parallel extraction regarding the pitch (F0 mean and standard deviation). We propose this additional analysis because pitch varies according to some demographic traits of the speaker (sex, age, height) and the literature presents opposite trends. For this task, we used Praat to have more flexibility in the manipulation of the extraction. We set the F0 range between 70 and 400 Hz (Patel et al., 2020).
Finally, we conducted a comparison between the results of the two methods excluding female participants to verify if the trend of pitch changes when the participants are not mixed.
Results: Table 1 shows the features selected between the ones extracted. They are related to prosody, quality of voice, loudness, and spectral distribution.
Jitter, shimmer and HNR are usually investigated together to describe the emotional prosody and the quality of voice. The same trend found on our corpus is recorded in previous studies on languages other than Italian (Bone et al. 2015; Kissine & Geelhand 2019). Moreover, spectral flux is usually investigated together with shimmer and jitter to describe speech impairments (Haider et al., 2019). Nevertheless, if we consider the studies related to autistic speech, there are few that describe this feature because of the different methodologies used during the extraction.
Finally, the values of pitch extracted by eGeMAPS and Praat show the same trend. It is higher in ASD than in controls, both if we considered the corpus mixed and the one with only the male speakers. However, the pitch does not show a statistically significant difference between the two groups (Table 2).
Conclusions: These results, although preliminary, seem to confirm the presence of phonetic alterations of speech associated with the disorder. Further studies could improve the accuracy of the pipeline proposed by doing a qualitative analysis of the results and considering other linguistic and paralinguistic domains (e.g., morphological, pragmatic, and gestural analysis).
},
	booktitle    = {The 22nd International Society for Autism Research (INSAR)},
	author       = {Beccaria, Federica and Gagliardi, Gloria and Kokkinakis, Dimitrios},
	year         = {2023},
}

@misc{themistocleous-etal-2023-assessing-331090,
	title        = {Assessing Language Disorders using Artificial Intelligence: a Paradigm Shift
},
	abstract     = {Speech, language, and communication deficits are present in most neurodegenerative syndromes. They enable the early detection, diagnosis, treatment planning, and monitoring of neurocognitive disease progression as part of traditional neurological assessment. Nevertheless, standard speech and language evaluation is time-consuming and resource-intensive for clinicians. We argue that using machine learning methodologies, natural language processing, and modern artificial intelligence (AI) for Language Assessment is an improvement over conventional manual assessment. Using these methodologies, Computational Language Assessment (CLA) accomplishes three goals: (i) provides a neuro-cognitive evaluation of speech, language, and communication in elderly and high-risk individuals for dementia; (ii) facilitates the diagnosis, prognosis, and therapy efficacy in at-risk and language-impaired populations; and (iii) allows easier extensibility to assess patients from a wide range of languages. By employing AI models, CLA may inform neurocognitive theory on the relationship between language symptoms and their neural bases. Finally, it signals a paradigm shift by significantly advancing our ability to optimize the prevention and treatment of elderly individuals with communication disorders, allowing them to age gracefully with social engagement.
},
	author       = {Themistocleous, Charalambos and Tsapkini,  Kyrana and Kokkinakis, Dimitrios},
	year         = {2023},
	publisher    = {arXiv.org},
}

@inProceedings{kokkinakis-etal-2023-prevalence-324818,
	title        = {The Prevalence of mRNA Related Discussions during the Post-COVID-19 Era},
	abstract     = {Vaccinations are one of the most significant interventions to public health, but vaccine hesitancy and skepticism are raising serious concerns for a portion of the population in many countries, including Sweden. In this study, we use Swedish social media data and structural topic modeling to automatically identify mRNA-vaccine related discussion themes and gain deeper insights into how people’s refusal or acceptance of the mRNA technology affects vaccine uptake. Our point of departure is a scientific study published in February 2022, which seems to once again sparked further suspicion and concern and highlight the necessity to focus on issues about the nature and trustworthiness in vaccine safety. Structural topic modelling is a statistical method that facilitates the study of topic prevalence, temporal topic evolution, and topic correlation automatically. Using such a method, our research goal is to identify the current understanding of the mechanisms on how the public perceives the mRNA vaccine in the light of new experimental findings.},
	booktitle    = { Caring is Sharing – Exploiting the Value in Data for Health and Innovation / M. Hägglund et al. (eds.) Proceedings of the 33rd Medical Informatics Europe Conference (MIE2023), Gothenburg, Sweden, 22-25 May 2023},
	author       = {Kokkinakis, Dimitrios and Bruinsma, Sebastianus Cornelis Jacobus  and Hammarlin, Mia-Marie},
	year         = {2023},
	publisher    = {IOS Press},
	ISBN         = {978-1-64368-388-1},
}

@inProceedings{kokkinakis-etal-2023-analysis-330230,
	title        = {Analysis of mRNA-vaccine posts on Swedish Twitter data },
	abstract     = {The aim of this study was to use Swedish social media data to capture public perspectives and sentiments regarding the abovementioned study on possible effect of the novel mRNA vaccines that became massively available to the public during late 2021. The intention is to understand the key issues (topics/themes) that have captured public attention in Sweden, as well as the barriers and facilitators to successful or not mRNA vaccines.},
	booktitle    = {14th International Conference of Experimental Linguistics, Athens, Greece},
	author       = {Kokkinakis, Dimitrios and Bruinsma, Bastian and Hammarlin, Mia-Marie},
	year         = {2023},
}

@article{hammarlin-etal-2023-covid-329784,
	title        = {COVID-19 Vaccine Hesitancy: A Mixed Methods Investigation of Matters of Life and Death.},
	abstract     = {In this article, hesitancy towards COVID-19 vaccinations is investigated as a phenomenon  touching  upon  existential  questions.  We  argue  that  it encompasses  ideas  of  illness  and  health,  and  also  of  dying  and  fear  of suffering. Building on a specific strand within anti-vaccination studies, we conjecture that vaccine hesitancy is, to some extent, reasonable, and that this scepticism should be studied with compassion. Through a mixed methods approach, vaccine hesitancy, as it is being expressed in a Swedish digital open forum, is investigated and understood as, on the one hand, a perceived need of protecting one’s body from techno-scientific experiments, and thus the risk of becoming a victim of medicine itself. On the other hand, the community members  express  what  we  call  a  tacit  belief  in  modern  medicine by demonstrating their own “expert” pandemic knowledge. The analysis also shows how the COVID-19 pandemic triggers memories of another pandemic, namely the swine flu in 2009–2010, and what we term a medical crisis that occurred then, due to a vaccine thatcaused a rare but severe side effect in Sweden and elsewhere.},
	journal      = {Journal of Digital Social Research (JDSR)},
	author       = {Hammarlin, MIa-Marie and Kokkinakis, Dimitrios and Borin, Lars},
	year         = {2023},
	volume       = {5},
	number       = {4},
	pages        = {31--61},
}

@inProceedings{hammarlin-etal-2023-fearing-327373,
	title        = {Fearing mRNA: A Mixed Methods Study of Vaccine Rumours},
	abstract     = {The first mass-distributed vaccines based on mRNA technology were launched in 2021 to protect against COVID-19, sparking rumours among vaccine critical individuals that these “new” vaccines might be more dangerous to the health than other, “traditional” vaccines. Drawing on rumour theories and social cognitive perspectives, the aim of this chapter is to account for the purpose and the spreading of medical rumours that encircle mRNA COVID-19 vaccines. We ask: How are rumours concerning mRNA expressed and established? In terms of trust and distrust, what function do the rumours have? We take as our empirical case the fast spreading of a medical journal article written by a group of infectious medicine researchers at Lund University, Sweden, that spawned an already established vaccine rumour, and analyse Swedish-language tweets discussing mRNA vaccines posted between February 10, 2022 and November 10, 2022. Our study follows a mixed methods sequential explanatory design consisting of an initial computational distant reading analysis based on structural topic modeling, followed by a close qualitative reading and thematic analysis of the results. Our analysis shows how mRNA rumours are not primarily based on ignorance, but rather on distrust regarding the officially sanctioned, positive narrative of new vaccine technologies, expressed through what we term counter-scientific argumentation.},
	booktitle    = {NordMedia23: "Technological Takeover? Social and Cultural Implications – Promises and Pitfalls"},
	author       = {Hammarlin, Mia-Marie and Kokkinakis, Dimitrios and Miegel, Fredrik and Stoencheva, Jullietta},
	year         = {2023},
	address      = {Bergen, Norway},
}