Conference Agenda (All times are shown in Eastern Daylight Time)
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Paper Session 13: AI and Machine Learning Techniques
4:00pm - 5:30pm
Session Chair: Jiangen He, University of Tennessee, Knoxville, USA
Location:Rivers, Ballroom Level, Wyndham
4:00pm - 4:30pm ID: 257 / PS13: 1 Long Papers Confirmation 1: I/we acknowledge that all session authors/presenters have read and agreed to the ASIS&T Annual Meeting Policies found at https://www.asist.org/am22/submission-types-instructions/ Topics: Artificial Intelligence (machine learning; text mining; natural language processing; deep learning; value-sensitive AI design; transparent and explainable AI) Keywords: Ming of peer review comments, Multiple rounds peer review comments, Aspect extraction, Aspect clustering
Characterizing Peer Review Comments of Academic Articles in Multiple Rounds
Nanjing University of Science and Technology, People's Republic of China
Peer review can evaluate the quality of academic articles involving the evaluation of some aspects, e.g., methodology, experiment, and aspects are usually the critical sections, substance and properties of the article concerned by reviewers. Previous research on content mining of peer review did not distinguish the round of reviews. Detecting differences peer review comments among different rounds can help us to understand the focus change of the reviewers in the different rounds. This paper takes the Nature Communications as an example to build the corpora of peer reviews in multiple rounds. We correlate review rounds and citations and extract aspects from the corpora to analyze the round characteristics of review comments. We find that there is no significant correlation between the review rounds and the citations frequency, but when the number of rounds is within 1-3, there is a weak positive correlation between the review rounds and citations. Additionally, the reviewers tend to pay more attention to the results analysis and the significance of the work firstly, and then they will focus on the details of the article, such as diagrams. This study can provide new ideas for peer review mining and the application of bibliometrics.
4:30pm - 5:00pm ID: 234 / PS13: 2 Long Papers Confirmation 1: I/we acknowledge that all session authors/presenters have read and agreed to the ASIS&T Annual Meeting Policies found at https://www.asist.org/am22/submission-types-instructions/ Topics: Archives; Data Curation; and Preservation (archives; records; cultural heritage materials; digital data curation; digital libraries; digital humanities) Keywords: digital library, natural language processing, machine learning
Uncovering Black Fantastic: Piloting a Word Feature Analysis and Machine Learning Approach for Genre Classification
Nikolaus Nova Parulian1, Ryan Dubnicek1, Glen Worthey1, J. Stephen Downie1, Daniel Evans1, John Walsh2
1University of Illinois at Urbana-Champaign, USA; 2Indiana University, USA
Due to both the size of digital library collections and the inconsistencies in their genre bibliographic meta-data, as digital libraries grow and their contents are opened for computational analysis, finding materials of interest becomes a major challenge. This challenge increases for sub-genres and other categories of text data that are less distinct from the whole. This project pilots machine learning methods and word feature analysis for identifying Black Fantastic genre texts within the HathiTrust Digital Library. These texts are sometimes referred to as "Afrofuturism" but more commonly today described as "Black Fantastic," in which African Diaspora artists and creators engage with the intersections of race and technology in their works with a primary focus on world-building. Black Fantastic texts pose a challenge to genre classification, as they incorporate aspects of science fiction and fantasy with y with general characteristics of African Diaspora-produced literature. This paper presents and reports on results from a pilot predictive modeling process to computationally identify Black Fantastic texts using curated word feature sets for each class of data: general English-language fiction, Black-authored fiction, and Black Fantastic fiction.
5:00pm - 5:15pm ID: 127 / PS13: 3 Short Papers Confirmation 1: I/we acknowledge that all session authors/presenters have read and agreed to the ASIS&T Annual Meeting Policies found at https://www.asist.org/am22/submission-types-instructions/ Topics: Social Media and Social Computing (social media & analytics; information gatekeeping on social media; network theories & visualization; community informatics; online communities; digital youth; social informatics & computing; socio-technical design) Keywords: filter bubble, multi-viewpoint KOS, diverse similarity, ontologies, multi-perspective search and recommender systems
Turning Filter Bubbles into Bubblesphere with Multi-Viewpoint KOS and Diverse Similarity (1st place best short paper award)
Bar Ilan University, Israel
The filter bubble phenomenon and its negative societal effects have been extensively explored in the literature in the past decade. However, the ability of modern AI-based systems to create personalized information bubbles, that is, to classify similar contents and users into clusters according to their interests and behavior, can actually be quite beneficial if utilized and managed properly and ethically. In this article we present ongoing research that aims to refine such bubble-building smart systems by adopting an ethical, multi-perspective approach that allows for linking isolated bubbles into a consolidated bubblesphere and offering users a choice to explore diverse bubbles related to their topics of interest. To implement the proposed approach, content matching should be based on diverse similarity, which can be derived from a multi-viewpoint KOS. In addition, the study explores how such a multi-viewpoint KOS and bubblesphere can be constructed using Wikidata’s ranks and qualifiers.