FLAIRS-31 2018 AI4BigData

Special track: Artificial Intelligence for Big Social Data Analysis

Melbourne, Florida, USA, May 21-23, 2018


AI4BigData is the AAAI FLAIRS special track on the application of artificial intelligence tools for big data analysis. The track includes data-related tasks such as analysis, capture, curation, search, sharing, storage, transfer, visualization, and information privacy, with special focus on social data on the Web. Hence, the broader context of the track comprehends AI, web mining, information retrieval, natural language processing, and sentiment analysis.

Previous editions:

• AI4BigData'17 (AAAI FLAIRS-30, 22nd May 2017, Marco Island, Florida, USA)
• AI4BigData'16 (AAAI FLAIRS-29, 17th May 2016, Key Largo, Florida, USA)
• AI4BigData'15 (AAAI FLAIRS-28, 19th May 2015, Hollywood, Florida, USA)

RATIONALE
As the Web rapidly evolves, Web users are evolving with it. In an era of social connectedness, people are becoming increasingly enthusiastic about interacting, sharing, and collaborating through social networks, online communities, blogs, Wikis, and other online collaborative media. In recent years, this collective intelligence has spread to many different areas, with particular focus on fields related to everyday life such as commerce, tourism, education, and health, causing the size of the Social Web to expand exponentially.

The distillation of knowledge from such a large amount of unstructured information, however, is an extremely difficult task, as the contents of today's Web are perfectly suitable for human consumption, but remain hardly accessible to machines. The opportunity to capture the opinions of the general public about social events, political movements, company strategies, marketing campaigns, and product preferences has raised growing interest both within the scientific community, leading to many exciting open challenges, as well as in the business world, due to the remarkable benefits to be had from marketing and financial market prediction.

The main aim of AI4BigData is to explore the new frontiers of big data computing for opinion mining and sentiment analysis through machine learning techniques, knowledge-based systems, adaptive and transfer learning, in order to more efficiently retrieve and extract social information from the Web.

TOPICS
The Special Track aims to provide an international forum for researchers in the field of big data computing for opinion mining and sentiment analysis to share information on their latest investigations in social information retrieval and their applications both in academic research areas and industrial sectors. The broader context of the Special Track comprehends information retrieval, natural language processing, computationa social science, web mining, semantic web, and artificial intelligence. Topics of interest include but are not limited to:
• Sentiment Analysis: Polarity detection and emotion recognition
• Social Network Analysis: Community identification and authority discovery
• Visual Analytics: social media tools for navigation and visualization
• Trust, reputation, and recommendation systems
• Organization and group behavior on social media
• Cultural influences on use and adoption of social media
• Text categorization: Topic recognition and demographic identification
• Multi-modal affective computing and sentiment analysis
• Multi-domain and cross-domain evaluation
• Sentiment topic detection and trend discovery
• Predicting real-world phenomena based on social media
• Social innovation and change through social media
• Ethnographic studies of social media

The special track also welcomes papers on specific application domains of knowledge-based systems for big data analysis, e.g., influence networks, customer experience management, intelligent user interfaces, multimedia management, computer-mediated human-human communication, enterprise feedback management, surveillance, and art.

SUBMISSION GUIDELINES
Interested authors should format their papers according to AAAI formatting guidelines. Papers should not exceed 6 pages (4 pages for a poster) and are due by November 20, 2017. All FLAIRS papers are reviewed using a double blind process. Fake author names and affiliations must be used on submitted papers. Papers must be submitted as PDF through the EasyChair conference system, which can be accessed through the main conference web site. Authors should indicate the AI for Big Social Data Analysis special track for submissions. The proceedings of FLAIRS will be published by the AAAI. Authors of accepted papers will be required to sign a form transferring copyright of their contribution to AAAI. FLAIRS requires that there be at least one full author registration per paper. Paper submission site: https://easychair.org/conferences/?conf=flairs31

IMPORTANT DATES:
November 20, 2017:
Paper submission deadline
January 22, 2018:
Paper acceptance notification
February 5, 2018:
Poster abstract submission
February 12, 2018:
Poster abstract notification
February 19, 2018:
AUTHOR registration
February 26, 2018:
Camera ready version due
April 9, 2018:
Early registration
May 14, 2018:
Regular registration
May 21-23, 2018:
Conference!

CONFERENCE PROCEEDINGS
Papers will be refereed and all accepted papers will appear in the conference proceedings, which will be published by AAAI Press.

TRACK CO-CHAIRS:
• Viviana Patti, University of Turin (Italy)
• Eric Bell, Pacific Northwest National Laboratory (USA)

AI4BigData'17 (AAAI FLAIRS-30, 22nd May 2017, Marco Island, Florida, USA)


Submissions are invited to AI4BigData'17 to be held at AAAI FLAIRS-30 at Marco Island on 22nd May 2017.

TIMEFRAME
November 21st, 2016: Paper submission deadline
January 23rd, 2017: Notification of paper acceptance
February 6th, 2016: Poster abstract submission deadline
February 13th, 2017: Notification of poster acceptance
February 27th, 2017: Camera-ready of accepted papers
May 22nd, 2017: Special track date

SUBMISSION AND PROCEEDINGS
Submitted papers must be original, and not submitted concurrently to a journal or another conference. Double-blind reviewing will be provided, so submitted papers must use fake author names and affiliations. Papers must use the latest AAAI Press template, and must be submitted as PDF through EasyChair. There are three kinds of submissions: full papers (up to 6 pages), short papers (up to 4 pages), and poster abstracts (up to 250 words). Acceptance as a full paper entails a 20 minute presentation during a regular session, while short papers and abstracts will be required to participate in the poster session. Rejected full papers may still be accepted as short papers or poster abstracts. Selected, expanded versions of Special Track papers will be published in a follow-on Special Issue of Springer's Cognitive Computation journal.

ORGANIZERS
• Viviana Patti, University of Turin (Italy)
• Erik Cambria, Nanyang Technological University (Singapore)
• Eric Bell, Pacific Northwest National Laboratory (USA)
• Nathan Hodas, Pacific Northwest National Laboratory (USA)

AI4BigData'16 (AAAI FLAIRS-29, 17th May 2016, Key Largo, Florida, USA)


PROGRAM
13:40-13:45 Welcoming and introduction
13:45-14:05 Reducing Feature Set Explosion to Facilitate Real-World Review Spam Detection (Michael Crawford, Taghi Khoshgoftaar and Joseph Prusa)
14:05-14:25 GECKA3D: A 3D Game Engine for Commonsense Knowledge Acquisition (Erik Cambria, Tam Nguyen, Brian Cheng, Kenneth Kwok and Jose Sepulveda)
14:25-14:45 Term Ranker: A graph based re-ranking approach (Tahir Khan, Yukun Ma and Jung-Jae Kim)
14:45-15:05 Sentiment Classification Using Negation as a Proxy for Negative Sentiment (Bruno Ohana, Brendan Tierney and Sarah Jane Delany)
15:05-15:25 Enhancing Ensemble Learners with Data Sampling on High-Dimensional Imbalanced Tweet Sentiment Data (Joseph Prusa, Taghi Khoshgoftaar and Naeem Seliya)
15:25-15:30 Concluding remarks

ORGANIZERS
• Erik Cambria, Nanyang Technological University (Singapore)
• Viviana Patti, University of Turin (Italy)
• Amir Hussain, University of Stirling (UK)
• Newton Howard, MIT Media Laboratory (USA)

AI4BigData'15 (AAAI FLAIRS-28, 19th May 2015, Hollywood, Florida, USA)


PROGRAM
10:00-10:15 Welcoming and introduction
10:15-10:35 Arsemotica for arsmeteo-org: Emotion-driven Exploration of Online Art Collections (Viviana Patti, Federico Bertola and Antonio Lieto)
10:35-10:55 Discovering Emotions in the Wild: An Inductive Method to Identify Fine-grained Emotion Categories from Tweets (Jasy Liew Suet Yan)
10:55-11:15 Event Analysis in Social Media using Clustering of Heterogeneous Information Networks (Narumol Prangnawarat, Ioana Hulpus and Conor Hayes)
11:15-11:35 Hierarchical Fuzzy Spectral Clustering in Social Networks using Spectral Characterization (Scott Wahl and John Sheppard

11:35-13:45 Lunch break

13:45-14:05 Impact of Feature Selection Techniques for Tweet Sentiment Classification (Joseph Prusa, Taghi Khoshgoftaar and David Dittman)
14:05-14:25 GECKA: Game Engine for Commonsense Knowledge Acquisition (Erik Cambria, Dheeraj Rajagopal, Kenneth Kwok, and Jose Sepulveda)
14:25-14:45 Semantic Outlier Detection for Affective Common-Sense Reasoning and Concept-Level Sentiment Analysis (Erik Cambria and Giuseppe Melfi)
14:45-15:05 Discriminative Bi-term Topic Model for Headline-based Social News Clustering (Yunqing Xia, Nan Tang, Amir Hussain, and Erik Cambria)
15:05-15:15 Concluding remarks

ORGANIZERS
• Erik Cambria, Nanyang Technological University (Singapore)
• Amir Hussain, University of Stirling (UK)
• Newton Howard, MIT Media Laboratory (USA)