@article {775, title = {Multimodal mental health analysis in social media}, journal = {PLoS ONE}, year = {2020}, abstract = {

p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 9.5px Helvetica}

Depression is a major public health concern in the U.S. and globally. While successful early

identification and treatment can lead to many positive health and behavioral outcomes,

depression, remains undiagnosed, untreated or undertreated due to several reasons,

including denial of the illness as well as cultural and social stigma. With the ubiquity of social

media platforms, millions of people are now sharing their online persona by expressing their

thoughts, moods, emotions, and even their daily struggles with mental health on social

media. Unlike traditional observational cohort studies conducted through questionnaires

and self-reported surveys, we explore the reliable detection of depressive symptoms from

tweets obtained, unobtrusively. Particularly, we examine and exploit multimodal big (social)

data to discern depressive behaviors using a wide variety of features including individuallevel

demographics. By developing a multimodal framework and employing statistical techniques

to fuse heterogeneous sets of features obtained through the processing of visual,

textual, and user interaction data, we significantly enhance the current state-of-the-art

approaches for identifying depressed individuals on Twitter (improving the average F1-

Score by 5 percent) as well as facilitate demographic inferences from social media. Besides

providing insights into the relationship between demographics and mental health, our

research assists in the design of a new breed of demographic-aware health interventions.

}, keywords = {Explainable Machine Learning, Hypothesis Testing, National Language Processing, Prediction, Regression}, url = {https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0226248\&type=printable}, author = {Amir Hossein Yazdavar and Mohammad Saeid Mahdavinejad and Goonmeet Baja and William Romine and Amit Sheth and Amir Hassan Monadjemi and Krishnaprasad Thirunarayan and John M. Meddar and Annie Myers and Jyotishman Pathak and Pascal Hitzler} } @conference {777, title = {Mental Health Analysis Via Social Media Data, IEEE ICHI 2018}, booktitle = {IEEE, ICHI}, year = {2018}, author = {Amir Hossein Yazdavar and Mohammad Saied Mahdavinejad and Goonmeet Bajaj and Krishnaprasad Thirunarayan and Jyotishman Pathak and Amit Sheth} } @article {779, title = {Challenges of Sentiment Analysis for Dynamic Events}, year = {2017}, abstract = {

Efforts to assess people{\textquoteright}s sentiments on Twitter have suggested that Twitter could be a valuable resource for studying political sentiment and that it reflects the offline political landscape. Many opinion mining systems and tools provide users with people{\textquoteright}s attitudes toward products, people, or topics and their attributes/aspects. However, although it may appear simple, using sentiment analysis to predict election results is difficult, since it is empirically challenging to train a successful model to conduct sentiment analysis on tweet streams for a dynamic event such as an election. This article highlights some of the challenges related to sentiment analysis encountered during monitoring of the presidential election using Kno.e.sis{\textquoteright}s Twitris system.

}, author = {Monireh Ebrahimi and Amir Hossein Yazdavar and Amit Sheth} } @conference {778, title = {Relatedness-based Multi-Entity Summarization}, booktitle = {IJCAI}, year = {2017}, abstract = {

Representing world knowledge in a machine processable format is important as entities and their descriptions have fueled tremendous growth in knowledge-rich information processing platforms, services, and systems. Prominent applications of knowledge graphs include search engines (e.g., Google Search and Microsoft Bing), email clients (e.g., Gmail), and intelligent personal assistants (e.g., Google Now, Amazon Echo, and Apple{\textquoteright}s Siri). In this paper, we present an approach that can summarize facts about a collection of entities by analyzing their relatedness in preference to summarizing each entity in isolation. Specifically, we generate informative entity summaries by selecting: (i) inter-entity facts that are similar and (ii) intra-entity facts that are important and diverse. We employ a constrained knapsack problem solving approach to efficiently compute entity summaries. We perform both qualitative and quantitative experiments and demonstrate that our approach yields promising results compared to two other stand-alone state-ofthe-art entity summarization approaches.

}, author = {Kalpa Gunaratna and Amir Hossein Yazdavar and Krishnaprasad Thirunarayan and Amit Sheth and Gong Cheng} } @conference {776, title = {Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media}, booktitle = {ASONAM}, year = {2017}, abstract = {

With the rise of social media, millions of people are routinely expressing their moods, feelings, and daily struggles with mental health issues on social media platforms like Twitter. Unlike traditional observational cohort studies conducted through questionnaires and self-reported surveys, we explore the reliable detection of clinical depression from tweets obtained unobtrusively. Based on the analysis of tweets crawled from users with self-reported depressive symptoms in their Twitter profiles, we demonstrate the potential for detecting clinical depression symptoms which emulate the PHQ-9 questionnaire clinicians use today. Our study uses a semi-supervised statistical model to evaluate how the duration of these symptoms and their expression on Twitter (in terms of word usage patterns and topical preferences) align with the medical findings reported via the PHQ-9. Our proactive and automatic screening tool is able to identify clinical depressive symptoms with an accuracy of 68\% and precision of 72\%.

}, url = {https://dl.acm.org/doi/abs/10.1145/3110025.3123028}, author = {Amir Hossein Yazdavar}, editor = {Hussein S. Al-Olimat and Monireh Ebrahimi and Goonmeet Bajaj and Tanvi Banerjee and Krishnaprasad Thirunarayan and Jyotishman Pathak and Amit Sheth} } @conference {94, title = {Automatic Domain Identification for Linked Open Data}, booktitle = {2013 IEEE/WIC/ACM International Conferences on Web Intelligence, WI 2013}, year = {2013}, pages = {205{\textendash}212}, address = {Atlanta, GA, USA}, abstract = {

Linked Open Data (LOD) has emerged as one of the largest collections of interlinked structured datasets on the Web. Although the adoption of such datasets for applications is increasing, identifying relevant datasets for a specific task or topic is still challenging. As an initial step to make such identification easier, we provide an approach to automatically identify the topic domains of given datasets. Our method utilizes existing knowledge sources, more specifically Freebase, and we present an evaluation which validates the topic domains we can identify with our system. Furthermore, we evaluate the effectiveness of identified topic domains for the purpose of finding relevant datasets, thus showing that our approach improves reusability of LOD datasets.

}, keywords = {dataset search, Domain Identification, Linked Open Data Cloud}, doi = {10.1109/WI-IAT.2013.206}, url = {http://dx.doi.org/10.1109/WI-IAT.2013.206}, author = {Sarasi Lalithsena and Pascal Hitzler and Amit Sheth and Prateek Jain} } @inbook {174, title = {Alignment-based querying of linked open data}, booktitle = {On the Move to Meaningful Internet Systems: OTM 2012}, year = {2012}, pages = {807{\textendash}824}, publisher = {Springer}, organization = {Springer}, author = {Joshi, Amit Krishna and Prateek Jain and Pascal Hitzler and Peter Z. Yeh and Kunal Verma and Amit Sheth and Mariana Damova} } @conference {97, title = {Moving beyond SameAs with PLATO: Partonomy detection for Linked Data}, booktitle = {23rd ACM Conference on Hypertext and Social Media, HT {\textquoteright}12}, year = {2012}, pages = {33{\textendash}42}, publisher = {ACM}, organization = {ACM}, address = {Milwaukee, WI, USA}, abstract = {

The Linked Open Data (LOD) Cloud has gained significant traction over the past few years. With over 275 interlinked datasets across diverse domains such as life science, geography, politics, and more, the LOD Cloud has the potential to support a variety of applications ranging from open domain question answering to drug discovery.

Despite its significant size (approx. 30 billion triples), the data is relatively sparely interlinked (approx. 400 million links). A semantically richer LOD Cloud is needed to fully realize its potential. Data in the LOD Cloud are currently interlinked mainly via the owl:sameAs property, which is inadequate for many applications. Additional properties capturing relations based on causality or partonomy are needed to enable the answering of complex questions and to support applications.

In this paper, we present a solution to enrich the LOD Cloud by automatically detecting partonomic relationships, which are well-established, fundamental properties grounded in linguistics and philosophy. We empirically evaluate our solution across several domains, and show that our approach performs well on detecting partonomic properties between LOD Cloud data.

}, keywords = {Linked Open Data Cloud, Mereology, Part of Relation}, doi = {10.1145/2309996.2310004}, url = {http://doi.acm.org/10.1145/2309996.2310004}, author = {Prateek Jain and Pascal Hitzler and Kunal Verma and Peter Z. Yeh and Amit Sheth}, editor = {Ethan V. Munson and Markus Strohmaier} } @article {307, title = {Semantic Aspects of EarthCube}, year = {2012}, abstract = {

In this document, we give a high-level overview of selected Semantic (Web) technologies, methods, and other important considerations, that are relevant for the success of EarthCube. The goal of this initial document is to provide entry points and references for discussions between the Semantic Technologies experts and the domain experts within EarthCube. The selected topics are intended to ground the EarthCube roadmap in the state of the art in semantics research and ontology engineering.

We anticipate that this document will evolve as EarthCube progresses. Indeed, all EarthCube parties are asked to provide topics of importance that should be treated in future versions of this document.

}, author = {Pascal Hitzler and Krzysztof Janowicz and Gary Berg-Cross and Leo Obrst and Amit Sheth and Timothy Finin and Isabel Cruz} } @conference {403, title = {Semantics and Ontologies for EarthCube}, booktitle = {Workshop on GIScience in the Big Data Age, In conjunction with the seventh International Conference on Geographic Information Science 2012 (GIScience 2012)}, year = {2012}, address = {Columbus, Ohio, USA}, abstract = {

Semantic technologies and ontologies play an increasing role in scientific workflow systems and knowledge infrastructures. While ontologies are mostly used for the semantic annotation of metadata, semantic technologies enable searching metadata catalogs beyond simple keywords, with some early evidence of semantics used for data translation. However, the next generation of distributed and interdisciplinary knowledge infrastructures will require capabilities beyond simple subsumption reasoning over subclass relations. In this work, we report from the EarthCube Semantics Community by highlighting which role semantics and ontologies should play in the EarthCube knowledge infrastructure. We target the interested domain scientist and, thus, introduce the value proposition of semantic technologies in a non-technical language. Finally, we commit ourselves to some guiding principles for the successful implementation and application of semantic technologies and ontologies within EarthCube.

}, author = {Gary Berg-Cross and Isabel Cruz and Mike Dean and Tim Finin and Mark Gahegan and Pascal Hitzler and Hook Hua and Krzysztof Janowicz and Naicong Li and Philip Murphy and Bryce Nordgren and Leo Obrst and Mark Schildhauer and Amit Sheth and Krishna Sinha and Anne Thessen and Nancy Wiegand and Ilya Zaslavsky}, editor = {Krzysztof Janowicz and C. Kessler and T. Kauppinen and Dave Kolas and Simon Scheider} } @conference {99, title = {Contextual Ontology Alignment of LOD with an Upper Ontology: A Case Study with Proton}, booktitle = {The Semantic Web: Research and Applications - 8th Extended Semantic Web Conference, ESWC 2011}, volume = {6643}, year = {2011}, pages = {80{\textendash}92}, publisher = {Springer}, organization = {Springer}, address = {Heraklion, Crete, Greece}, abstract = {

The Linked Open Data (LOD) is a major milestone towards realizing the Semantic Web vision, and can enable applications such as robust Question Answering (QA) systems that can answer queries requiring multiple, disparate information sources. However, realizing these applications requires relationships at both the schema and instance level, but currently the LOD only provides relationships for the latter. To address this limitation, we present a solution for automatically finding schema-level links between two LOD ontologies {\textendash} in the sense of ontology alignment. Our solution, called BLOOMS+, extends our previous solution (i.e. BLOOMS) in two significant ways. BLOOMS+ 1) uses a more sophisticated metric to determine which classes between two ontologies to align, and 2) considers contextual information to further support (or reject) an alignment. We present a comprehensive evaluation of our solution using schema-level mappings from LOD ontologies to Proton (an upper level ontology) {\textendash} created manually by human experts for a real world application called FactForge. We show that our solution performed well on this task. We also show that our solution significantly outperformed existing ontology alignment solutions (including our previously published work on BLOOMS) on this same task.

}, doi = {10.1007/978-3-642-21034-1_6}, url = {http://dx.doi.org/10.1007/978-3-642-21034-1_6}, author = {Prateek Jain and Peter Z. Yeh and Kunal Verma and Reymonrod G. Vasquez and Mariana Damova and Pascal Hitzler and Amit Sheth}, editor = {Grigoris Antoniou and Marko Grobelnik and Elena Paslaru Bontas Simperl and Bijan Parsia and Dimitris Plexousakis and Pieter De Leenheer and Jeff Z. Pan} } @conference {114, title = {Linked Data Is Merely More Data}, booktitle = {Linked Data Meets Artificial Intelligence, Papers from the 2010 AAAI Spring Symposium}, year = {2010}, publisher = {AAAI}, organization = {AAAI}, address = {Stanford, California, USA}, abstract = {

In this position paper, we argue that the Linked Open Data (LoD) Cloud, in its current form, is only of limited value for furthering the Semantic Web vision. Being merely a weakly linked {\textquotedblleft}triple collection,{\textquotedblright} it will only be of very limited bene- fit for the AI or Semantic Web communities. We describe the corresponding problems with the LoD Cloud and give directions for research to remedy the situation.

}, url = {http://www.aaai.org/ocs/index.php/SSS/SSS10/paper/view/1130}, author = {Prateek Jain and Pascal Hitzler and Peter Z. Yeh and Kunal Verma and Amit Sheth}, editor = {Dan Brickley and Vinay K. Chaudhri and Harry Halpin and Deborah McGuinness} } @conference {111, title = {Ontology Alignment for Linked Open Data}, booktitle = {The Semantic Web - ISWC 2010 - 9th International Semantic Web Conference, ISWC 2010}, volume = {6496}, year = {2010}, pages = {402{\textendash}417}, publisher = {Springer}, organization = {Springer}, address = {Shanghai, China}, abstract = {

The Web of Data currently coming into existence through the Linked Open Data (LOD) effort is a major milestone in realizing the Semantic Web vision. However, the development of applications based on LOD faces difficulties due to the fact that the different LOD datasets are rather loosely connected pieces of information. In particular, links between LOD datasets are almost exclusively on the level of instances, and schema-level information is being ignored. In this paper, we therefore present a system for finding schema-level links between LOD datasets in the sense of ontology alignment. Our system, called BLOOMS, is based on the idea of bootstrapping information already present on the LOD cloud. We also present a comprehensive evaluation which shows that BLOOMS outperforms state-of-the-art ontology alignment systems on LOD datasets. At the same time, BLOOMS is also competitive compared with these other systems on the Ontology Evaluation Alignment Initiative Benchmark datasets.

}, doi = {10.1007/978-3-642-17746-0_26}, url = {http://dx.doi.org/10.1007/978-3-642-17746-0_26}, author = {Prateek Jain and Pascal Hitzler and Amit Sheth and Kunal Verma and Peter Z. Yeh}, editor = {Peter F. Patel-Schneider and Yue Pan and Pascal Hitzler and Peter Mika and Lei Zhang and Jeff Z. Pan and Ian Horrocks and Birte Glimm} } @conference {112, title = {Provenance Context Entity (PaCE): Scalable Provenance Tracking for Scientific RDF Data}, booktitle = {Scientific and Statistical Database Management, 22nd International Conference, SSDBM 2010}, volume = {6187}, year = {2010}, pages = {461{\textendash}470}, publisher = {Springer}, organization = {Springer}, address = {Heidelberg, Germany}, abstract = {

The Semantic Web Resource Description Framework (RDF) format is being used by a large number of scientific applications to store and disseminate their datasets. The provenance information, describing the source or lineage of the datasets, is playing an increasingly significant role in ensuring data quality, computing trust value of the datasets, and ranking query results. Current Semantic Web provenance tracking approaches using the RDF reification vocabulary suffer from a number of known issues, including lack of formal semantics, use of blank nodes, and application-dependent interpretation of reified RDF triples that hinders data sharing. In this paper, we introduce a new approach called Provenance Context Entity (PaCE) that uses the notion of provenance context to create provenance-aware RDF triples without the use of RDF reification or blank nodes. We also define the formal semantics of PaCE through a simple extension of the existing RDF(S) semantics that ensures compatibility of PaCE with existing Semantic Web tools and implementations. We have implemented the PaCE approach in the Biomedical Knowledge Repository (BKR) project at the US National Library of Medicine to support provenance tracking on RDF data extracted from multiple sources, including biomedical literature and the UMLS Metathesaurus. The evaluations demonstrate a minimum of 49\% reduction in total number of provenancespecific RDF triples generated using the PaCE approach as compared to RDF reification. In addition, using the PACE approach improves the performance of complex provenance queries by three orders of magnitude and remains comparable to the RDF reification approach for simpler provenance queries.\ 

}, keywords = {Biomedical knowledge repository, Context theory, Provenance context entity, Provenance Management Framework., Provenir ontology, RDF reification}, doi = {10.1007/978-3-642-13818-8_32}, url = {http://dx.doi.org/10.1007/978-3-642-13818-8_32}, author = {Satya S. Sahoo and Olivier Bodenreider and Pascal Hitzler and Amit Sheth and Krishnaprasad Thirunarayan}, editor = {Michael Gertz and Bertram Lud{\"a}scher} } @conference {168, title = {Ontology Driven Integration of Biology Experiment Data}, booktitle = {Ohio Collaborative Conference on BioInformatics (OCCBIO 2009), Posters \& Demos}, year = {2009}, address = {Cleveland, OH, USA}, author = {Raghava Mutharaju and Satya S. Sahoo and D. Brent Weatherly and Pramod Anantharam and Flora Logan and Amit Sheth and Rick Tarleton} } @conference {162, title = {Ontology-Driven Provenance Management in eScience: An Application in Parasite Research}, booktitle = {On the Move to Meaningful Internet Systems: OTM 2009, Confederated International Conferences, CoopIS, DOA, IS, and ODBASE 2009, Proceedings, Part II}, volume = {5871}, year = {2009}, pages = {992{\textendash}1009}, publisher = {Springer}, organization = {Springer}, address = {Vilamoura, Portugal}, abstract = {

Provenance, from the French word {\textquotedblleft}provenir{\textquotedblright}, describes the lineage or history of a data entity. Provenance is critical information in scientific applications to verify experiment process, validate data quality and associate trust values with scientific results. Current industrial scale eScience projects require an end-to-end provenance management infrastructure. This infrastructure needs to be underpinned by formal semantics to enable analysis of large scale provenance information by software applications. Further, effective analysis of provenance information requires well-defined query mechanisms to support complex queries over large datasets. This paper introduces an ontology-driven provenance management infrastructure for biology experiment data, as part of the Semantic Problem Solving Environment (SPSE) for Trypanosoma cruzi (T.cruzi). This provenance infrastructure, called T.cruzi Provenance Management System (PMS), is underpinned by (a) a domain-specific provenance ontology called Parasite Experiment ontology, (b) specialized query operators for provenance analysis, and (c) a provenance query engine. The query engine uses a novel optimization technique based on materialized views called materialized provenance views (MPV) to scale with increasing data size and query complexity. This comprehensive ontology-driven provenance infrastructure not only allows effective tracking and management of ongoing experiments in the Tarleton Research Group at the Center for Tropical and Emerging Global Diseases (CTEGD), but also enables researchers to retrieve the complete provenance information of scientific results for publication in literature.

}, doi = {10.1007/978-3-642-05151-7_18}, url = {http://dx.doi.org/10.1007/978-3-642-05151-7_18}, author = {Satya S. Sahoo and D. Brent Weatherly and Raghava Mutharaju and Pramod Anantharam and Amit Sheth and Rick Tarleton}, editor = {Robert Meersman and Tharam S. Dillon and Pilar Herrero} } @conference {163, title = {Spatio-Temporal-Thematic Analysis of Citizen Sensor Data: Challenges and Experiences}, booktitle = {Web Information Systems Engineering - WISE 2009, 10th International Conference}, volume = {5802}, year = {2009}, pages = {539{\textendash}553}, publisher = {Springer}, organization = {Springer}, address = {Poznan, Poland}, abstract = {

We present work in the spatio-temporal-thematic analysis of citizen-sensor observations pertaining to real-world events. Using Twitter as a platform for obtaining crowd-sourced observations, we explore the interplay between these 3 dimensions in extracting insightful summaries of social perceptions behind events. We present our experiences in building a web mashup application, Twitris [1] that extracts and facilitates the spatio-temporal-thematic exploration of event descriptor summaries.

}, doi = {10.1007/978-3-642-04409-0_52}, url = {http://dx.doi.org/10.1007/978-3-642-04409-0_52}, author = {Meenakshi Nagarajan and Karthik Gomadam and Amit Sheth and Ajith Ranabahu and Raghava Mutharaju and Ashutosh Jadhav}, editor = {Gottfried Vossen and Darrell D. E. Long and Jeffrey Xu Yu} } @conference {169, title = {Trykipedia: Collaborative Bio-Ontology Development using Wiki Environment}, booktitle = {Ohio Collaborative Conference on BioInformatics (OCCBIO 2009), Posters \& Demos}, year = {2009}, address = {Cleveland, OH, USA}, author = {Pramod Anantharam and Satya S. Sahoo and D. Brent Weatherly and Flora Logan and Raghava Mutharaju and Amit Sheth and Rick Tarleton} } @conference {165, title = {Twitris: Socially Influenced Browsing}, booktitle = {Semantic Web Challenge at the 8th International Semantic Web Conference (ISWC 2009)}, year = {2009}, address = {Washington DC, USA}, abstract = {

In this paper, we present Twitris, a semantic Web application that facilitates browsing for news and information, using social perceptions as the fulcrum. In doing so we address challenges in large scale crawling, processing of real time information, and preserving spatiotemporal-thematic properties central to observations pertaining to realtime events. We extract metadata about events from Twitter and bring related news and Wikipedia articles to the user. In developing Twitris, we have used the DBPedia ontology.

}, author = {Ashutosh Jadhav and Wenbo Wang and Raghava Mutharaju and Pramod Anantharam and Vinh Nguyen and Amit Sheth and Karthik Gomadam and Meenakshi Nagarajan and Ajith Ranabahu} }