author = {Nia Dowell and Leah Windsor and Mae-Lynn Germany and Francisco Iacobelli and Art Graesser},
  booktitle = {Proceedings of the 15th meeting of the Society for Text and Discourse.},
  title = {The Partisan Divide: A Computational Linguistic Analysis of Bias in the Senate},
  url = {},
  year = {2015}
  author = {Adler, Rachel F and Iacobelli, Francisco and Gutstein, Yehuda},
  booktitle = {Proceedings of the 10th International conference on Persuasive Technology PERSUASIVE 2015},
  title = {{Are You Convinced? A Wizard of Oz Study to Test Emotional vs. Rational Persuasion Strategies in Dialogues}},
  year = {2015}
  author = {Mart\'{\i}nez, V\'{\i}ctor R. and Perez, Luis Eduardo and Iacobelli, Francisco and {Suarez Boj\'{o}rquez}, Salvador and Gonzalez, Victor M.},
  booktitle = {proceedings of the 7th Mexican Conference on Pattern Recognition (MCPR15)},
  title = {{Semi-Supervised Approach to Named Entity Recognition in Spanish Applied to a Real-World Conversational System}},
  year = {2015}
  author = {Alastair, Gill and Iacobelli, Francisco},
  booktitle = {Proceedings of the 14th meeting of the Society for Text and Discourse.},
  title = {{Generative Topic Modeling for Concept Understanding}},
  url = {},
  year = {2014}
  author = {Chaney, Joseph and Fiss, Andrew and Iacobelli, Francisco and Carey, Paul E. Jr.},
  booktitle = {In GPS for Graduate School: Students Share Their Stories.},
  chapter = {6},
  editor = {Smith, Mark J. T. and Browne, Mary M.},
  title = {{Balancing Graduate School and Family}},
  url = {},
  year = {2014}
  author = {Iacobelli, Francisco and Culotta, Bf A},
  booktitle = {ICWSM Workshop on Personality Classification},
  keywords = {crf,personality},
  title = {{Too Neurotic, Not too Friendly: Structured Personality Classification on Textual Data}},
  url = {\_cameraReady.pdf},
  year = {2013}
  author = {Iacobelli, Francisco},
  howpublished = {Paperback},
  isbn = {124904300X},
  month = jul,
  publisher = {ProQuest, UMI Dissertation Publishing},
  title = {{Augmenting News Stories With Distinct Information.}},
  url = {\&path=ASIN/124904300X},
  year = {2012}
  author = {Iacobelli, Francisco and Nichols, Nathan and Birnbaum, Larry and Hammond, Kristian},
  booktitle = {Human Computer Interaction: The Agency Perspective. Studies in Computational Intelligence},
  doi = {10.1007/978-3-642-25691-2\_16},
  isbn = {9783642256905},
  issn = {1860949X},
  pages = {375--387},
  title = {{Information finding with robust entity detection: The case of an online news reader}},
  url = {\%2F978-3-642-25691-2\_16},
  volume = {396},
  year = {2012}
  author = {Gill, Alastair and Iacobelli, Francisco and Gilbert, Nigel},
  journal = {21\^{}\{st\} meeting of the Society for Text and Discourse},
  keywords = {*file-import-14-02-28},
  title = {{The Projection of Quality and Reputation in Scholarly Journal Description}},
  url = {\_2011.pdf},
  year = {2011}
  abstract = {Personality is a fundamental component of an individual’s affective behavior. Previous work on personality classification has emerged from disparate sources: Varieties of algorithms and feature-selection across spoken and written data have made comparison difficult. Here, we use a large corpus of blogs to compare classification feature selection; we also use these results to identify characteristic language information relating to personality. Using Support Vector Machines, the best accuracies range from 84.36\% (openness to experience) to 70.51\% (neuroticism). To achieve these results, the best performing features were a combination of: (1) stemmed bigrams; (2) no exclusion of stopwords (i.e. common words); and (3) the boolean, presence or absence of features noted, rather than their rate of use. We take these findings to suggest that both the structure of the text and the presence of common words are important. We also note that a common dictionary of words used for content analysis (LIWC) performs less well in this classification task, which we propose is due to their conceptual breadth. To get a better sense of how personality is expressed in the blogs, we explore the best performing features and discuss how these can provide a deeper understanding of personality language behavior online.},
  author = {Iacobelli, Francisco and Gill, Aj and Nowson, Scott and Oberlander, Jon},
  journal = {Proceedings of the 4th international conference on Affective computing and intelligent interaction},
  keywords = {machine learning,personality classification},
  pages = {568--577},
  title = {{Large scale personality classification of bloggers}},
  url = {\_71},
  year = {2011}
  abstract = {A study comparing MakeMyPage (automatic content generation, social media for ranking) to social media websites and automatic aggregators.},
  address = {Raleigh, NC. USA},
  author = {Iacobelli, Francisco and Birnbaum, Larry and Hammond, Kristian},
  booktitle = {Third workshop on Mashups, Enterprise Mashups and Lightweight composition on the web (MEM2010) at WWW2010},
  keywords = {aggregation,media,search,social},
  month = apr,
  title = {{Synergy Between Automatic Content Generation and Social Media}},
  url = {},
  year = {2010}
  abstract = {The Web makes it possible for news readers to learn more about virtually any story that interests them. Media outlets and search engines typically augment their information with links to similar stories. It is up to the user to determine what new information is added by them, if any. In this paper we present Tell Me More, a system that performs this task automatically: given a seed news story, it mines the web for similar stories reported by different sources and selects snippets of text from those stories which offer new information beyond the seed story. New content may be classified as supplying: additional quotes, additional actors, additional figures and additional information depending on the criteria used to select it. In this paper we describe how the system identifies new and informative content with respect to a news story. We also how that providing an explicit categorization of new information is more useful than a binary classification (new/not-new). Lastly, we show encouraging results from a preliminary evaluation of the system that validates our approach and encourages further study.},
  author = {Iacobelli, Francisco and Birnbaum, Larry and Hammond, Kristian J.},
  booktitle = {IUI '10 Proceedings of the 15th international conference on Intelligent user interfaces},
  keywords = {dimensions of similarity,information retrieval,new information detection},
  pages = {81--90},
  title = {{Tell me more, not just more of the same}},
  url = {\_IUI\_cameraReady.pdf},
  year = {2010}
  abstract = {Journalists and editors work under pressure to collect relevant details and background information about specific events. They spend a significant amount of time sifting through documents and finding new information such as facts, opinions or stakeholders (i.e. people, places and organizations that have a stake in the news). Spotting them is a tedious and cognitively intense process. One task, essential to this process, is to find and keep track of stakeholders. This task is taxing cognitively and in terms of memory. Tell Me More offers an automatic aid to this task. Tell Me More is a system that, given a seed story, mines the web for similar stories reported by different sources and selects only those stories which offer new information with respect to that original seed story. Much like a journalist, the task of detecting named entities is central to its success. In this paper we briefly describe Tell Me More and, in particular, we focus on Tell Me More’s entity detection component. We describe an approach that combines off-the-shelf named entity recognizers (NERs) with WPED, a publicly available NER that uses Wikipedia as its knowledge base. We show significant increase in precision scores with respect to traditional NERs. Lastly, we present an overall evaluation of Tell Me More using this approach.},
  author = {Iacobelli, Francisco and Nichols, Nathan and Birnbaum, Larry and Hammond, Kristian},
  journal = {Artificial Intelligence},
  pages = {32--37},
  title = {{Finding New Information via Robust Entity Detection}},
  url = {$\backslash$n\_20100615.pdf\_draft.pdf},
  year = {2010}
  abstract = {Poster presenting ideas and preliminary findings on comp. linguisitics techniques to assess writing style of essays of divinity students.},
  author = {Paterson, Jessie and Lange, Christian and Akhtar, Iqbal and Iacobelli, Francisco and Anderson, Paul and Leonhard, Annette},
  booktitle = {eAssessment Scotland (EAS2010)},
  keywords = {assessment,automatic,computational,essay,humanitites,linguistics},
  month = sep,
  title = {{Exploring the use of computational linguistics for automated formative feedback in the humanitites}},
  url = {\_abstract.php?paper\_id=13391},
  year = {2010}
  abstract = {This collaborative, explorative project has been investigating the possible role of computational linguistic techniques in providing automated formative feedback on student's written work - as opposed to their use in summative "automated marking". The student work included both traditional essays, and collaborative work using Wikis, by students in the School of Divinity, University of Edinburgh . The project included two phases:In the first phase, we attempted to identify the criteria that are used in practice by academic staff when marking student work. We approached this by analysing the written feedback provided on samples of student work - this was discussed with the staff and subsequently refined to produce an explicit list of criteria. We then used a number of automated tools (Wordsmith, LIWC) to identify certain "surface" features which distinguished between the "good" and "bad" written work. The paper will describe the identified criteria in detail, and discuss their relationship to the automatically identified features.In the second phase, we surveyed various computational techniques to determine if they could potentially be used to identify some of the criteria automatically. These techniques included analysis of "surface" features - such as the use of the passive or active voice, or appropriate referencing - as well as "deeper" techniques such as Latent Semantic Analysis (LSA) and "TextTiling". This identified a range of promising approaches, and some of these were tested, using real data from student work. The paper describes these techniques, and results in more detail.We conclude that:(1) There is a real potential to produce an automated tool which uses a range of techniques to provide practically useful formative feedback on student's written work.(2) The academic staff felt that the process of rigorously defining the criteria had been of benefit to their manual marking in the future.(3) We initially expected to apply the same criteria to the Wikis and the traditional essays. However, we discovered that these require different approaches which led to different styles and marking criteria.},
  author = {Paterson, Jessie and Lange, Christian and Akhtar, Iqbal and Iacobelli, Francisco and Anderson, Paul and Leonhard, Annette},
  booktitle = {International Conference of Education, Research and Innovation (ICERI) 2010},
  isbn = {978-84-614-2439-9},
  keywords = {education,linguistics,tools},
  month = nov,
  pages = {5303--5312},
  title = {{Exploring The Use Of Computational Linguistics For Automated Formative Feedback In The Humanities}},
  year = {2010}
  annote = {After careful comparison of ML algorithms and feature selection on a dataset of approx 2400 bloggers, we find that bigrams are the best classifiers of personality in blogs when using an SVM. This could point to the fact that linguistic features may not capture details of language use essential to personality detection.},
  author = {Iacobelli, Francisco and Gill, Alastair J and Nowson, Scott and Oberlander, Jon},
  booktitle = {19th Annual Meeting of the Society for Text and Discourse},
  keywords = {classification,personality},
  month = jul,
  title = {{Classification of Personality In Large Blog Data}},
  year = {2009}
  address = {San Jose, CA},
  author = {Iacobelli, Francisco and Hammond, Kristian J and Birnbaum, Larry},
  booktitle = {3rd International Conference of Weblogs and Social Media},
  keywords = {aggregation,automatic,content,media,social},
  month = may,
  title = {{MakeMyPage: Social Media Meets Automatic Content Generation}},
  url = {},
  year = {2009}
  abstract = {In this paper we present the design, development and initial evaluation of a virtual peer that models ethnicity through culturally authentic verbal and non-verbal behaviors. The behaviors chosen for the implementation come from an ethnographic study with African-American and Caucasian children and the evaluation of the virtual peer consists of a study in which children interacted with an African American or a Caucasian virtual peer and then assessed its ethnicity. Results suggest that it may be possible to tip the ethnicity of a embodied conversational agent by changing verbal and non-verbal behaviors instead of surface attributes, and that children engage with those virtual peers in ways that have promise for educational applications.},
  author = {Iacobelli, Francisco and Cassell, Justine},
  booktitle = {Intelligent Virtual Agents},
  chapter = {6},
  doi = {10.1007/978-3-540-74997-4\_6},
  isbn = {3907507843},
  keywords = {culture,embodied conversational agents,ethnicity,virtual peers},
  pages = {57--63},
  publisher = {Springer-Verlag, Berlin Heidelberg},
  series = {Lecture Notes in Computer Science},
  title = {{Ethnic Identity and Engagement in Embodied Conversational Agents}},
  url = {\_ethnicECA.pdf},
  volume = {4722},
  year = {2007}
  abstract = {This paper examines language similarity in messages over time in an online community of adolescents from around the world using three computational measures: Spearman's Correlation Coefficient, Zipping and Latent Semantic Analysis. Results suggest that the participants' language diverges over a six-week period, and that divergence is not mediated by demographic variables such as leadership status or gender. This divergence may represent the introduction of more unique words over time, and is influenced by a continual change in subtopics over time, as well as community-wide historical events that introduce new vocabulary at later time periods. Our results highlight both the possibilities and shortcomings of using document similarity measures to assess convergence in language use.},
  address = {Morristown, NJ, USA},
  author = {Huffaker, David and Jorgensen, Joseph and Iacobelli, Francisco and Tepper, Paul and Cassell, Justine},
  booktitle = {ACTS '09: Proceedings of the HLT-NAACL 2006 Workshop on Analyzing Conversations in Text and Speech},
  keywords = {language,over,similarity,time},
  pages = {15--22},
  publisher = {Association for Computational Linguistics},
  title = {{Computational measures for language similarity across time in online communities}},
  url = {\_CompMeasures.pdf},
  year = {2006}

This file was generated by bibtex2html 1.96.