The 11th ACM International Conference on Web Search and Data Mining

Los Angeles, California, USA, Feb. 5-9, 2018.


In case of limited space due to popularity, preference will be given to invited participants first.

International Workshop On Heterogeneous Networks Analysis And Mining

Shobeir Fakhraei (USC Information Sciences Institute), Yanen Li (Snap Inc.), Yizhou Sun (UCLA), Tim Weninger (University of Notre Dame)
Graphs naturally represent a host of processes, including interactions between people on social or communication networks, links between webpages on the World Wide Web, protein interactions in biological networks, movement in transportation networks, electricity delivery in smart energy grids, relations in bibliographic data, and many others. In such scenarios, graphs that model real-world networks are typically heterogeneous, multi-modal, and multi-relational. In the era of big data, as more varieties of interconnected structured and semi-structured data are becoming available, the importance of leveraging this heterogeneous and multi-relational nature of networks in being able to effectively mine and learn this kind of data is becoming more evident. The objective of this workshop is to bring together researchers from a variety of related areas, and discuss commonalities and differences in challenges faced, survey some of the different approaches, and provide a forum to present and learn about some of the most cutting-edge research in this area. As an outcome, we expect participants to walk away with a better sense of the variety of different methods and tools available for heterogenous network mining and analysis, and an appreciation for some of the interesting emerging applications, as well as the challenges that accompany these applications. There are many challenges involved in effectively mining and learning from this kind of data, including:
  • Understanding the different techniques applicable, including heterogeneous graph mining algorithms, graphical models, latent variable models, matrix factorization methods and more.
  • Dealing with the heterogeneity of the data.
  • The common need for information integration and alignment.
  • Handling dynamic and changing data.
  • Addressing each of these issues at scale.
Traditionally, a number of subareas have contributed to this space: communities in graph mining, learning from structured data, statistical relational learning, and, moving beyond subdisciplines in computer science, social network analysis, and, more broadly network science.

IFUP: Workshop on Multi-dimensional Information Fusion for User Modeling and Personalization

Feida Zhu (Singapore Management University, Singapore), Yongfeng Zhang (University of Massachusetts Amherst, USA), Neil Yorke-Smith (Delft University of Technology, and American University of Beirut), Guibing Guo (Northeastern University, China), Xu Chen (Tsinghua University, China)

Real-world systems accumulate large-scale and various kinds of multimodal information rapidly, including but not limited to text, image, video, audio, social relations, meta data, etc. Such information has been incorporated in many recommendation models and systems to promote the performance and user experience, giving rise to some of the recent and/or classical topics in recommender system, such as review-based recommendation, image-based recommendation, explainable recommendation, deep learning for recommendation, POI recommendation, video/music recommendation, and many others.

Integrating multimodal side information is not a trivial task, because information may be either homogenous or heterogeneous, which requires more advanced method for information fusion and alignment. Besides, different information may play distinct roles for different domains, users, and tasks, and the availability of new information source may even lead to completely new recommendation research tasks. As a result, it needs significant efforts from both the research community and industry to promote the recommendation system research and application in face of the various information sources.

IFUP 2018 aims to provide a dedicated forum for discussing open problems, challenges and innovative research approaches in fusing multi-dimensional information for user modelling and recommender systems. The major goal of this workshop is to promote advanced recommendation solutions that can be easily and readily deployed to meet industrial demands for personalized recommendation.

Workshop on Two-sided Marketplace Optimization: Search, Pricing, Matching & Growth

Mihajlo Grbovic (Senior Research Scientist, Airbnb), Thanasis Noulas (Senior Research Scientist, Airbnb)
In recent years two sided marketplaces have emerged as viable business models in many real world applications. In particular, we have moved from the social network paradigm to a network with two distinct types of participants representing supply and demand of a specific good. Examples industries include but are not limited to accommodation (Airbnb,, HomeAway), video content (YouTube, Dailymotion), Ridesharing (Uber, Didi, Lyft), online shops (Etsy, Ebay), music (Soundcloud), app stores (Apple App Store, Google App Store) and job sites (LinkedIn). The traditional research in most of these industries focused on satisfying the demand. OTAs would sell hotel accommodation, TV networks would broadcast their own content or taxi companies would own their own vehicle fleet. In modern examples like Airbnb, YouTube or Uber the platforms have customers on the supply side as well, and have to optimize their models taking into consideration host preferences, youtube producers and drivers.
The objective of this workshop is to bring practitioners of two-sided marketplaces together and discuss the evolution of ranking, recommendation, matching and growth data mining to account for the dual nature of the problem.

The 5th International Workshop on Social Web for Disaster Management (SWDM'18)

Yu-Ru Lin (University of Pittsburgh, USA), Carlos Castillo (Pompeu Fabra University, Spain), Jie Yin (CSIRO, Australia)

The Social Web for Disaster Management (SWDM) international workshop series, now in its fifth edition, is a key venue for computer scientists, government officials, emergency agencies, and other interested participants to discuss technical issues and research challenges in the understanding of digitally-mediated, social and technical systems during mass emergencies. The workshop theme for this year is "Collective Sensing, Trust, and Resilience in Global Crises," through which we aim to facilitate interdisciplinary discussion on a range of emergent challenges facing the world, from harnessing big data on the Web that facilitates disaster and risk management, to engaging citizen participation in disaster response, establishing trust in global and local communities, designing socio-technical systems, and building resilience to disasters through Internet of Things and ubiquitous intelligence.

To reflect the broad scope of topics relevant to this year's theme, we encourage submissions on interdisciplinary research topics within the contexts of crisis informatics, risk, and disaster management. The workshop will include a variety of submissions including regular papers, short papers, and software system demonstrations in addition to its invited talks.

GTA3 2018: Workshop on Graph Techniques for Adversarial Activity Analytics

Jiejun Xu (HRL Laboratories, Contact), Hanghang Tong (Arizona State University), Tsai-Ching Lu (HRL Laboratories), Jingrui He (Arizona State University), Nadya Bliss (Arizona State University)
Networks are natural analytic tools in modeling adversarial activities (e.g., human trafficking, illicit drug production, terrorist financial transaction) using different intelligence data sources. However, such activities are often covert and embedded across multiple domains and contexts. They are generally not detectable and recognizable from the perspective of an isolated network, and only become apparent when multiple networks are analyzed in a joint manner. Thus, one of the main research topics in modeling adversarial activities is to develop effective techniques to align and fuse information from different networks into a unified representation for global analysis. Based on the combined network representation, an equally important research topic is on detecting and matching indicating patterns to recognize the underlining adversarial activities in the integrated network. Two key challenge problems involved in the modeling process include: Network alignment and merging - develop accurate and scalable methods for mapping of nodes across heterogeneous networks based on different associational and causal dependencies.; Sub-graph detection and matching - develop robust and efficient algorithms for richly attributed networks to support recognition of complex query patterns for networks. The focus of this workshop is to gather together the researchers from all relevant fields to share their experience and opinions on graph mining techniques in the era of big data, with emphasis on two fundamental problems – “Connecting the dots” and “finding a needle in a haystack”, in the context of graph-based adversarial activity analytics.

First Workshop on Knowledge Base Construction, Reasoning and Mining (KBCOM 2018)

Xiang Ren (USC), Craig Knoblock (USC/ISI), William Wang (UCSB), Yu Su (UCSB)
The success of data mining and search technologies is largely attributed to the efficient and effective analysis of structured data. Construction of a well-structured, machine-actionable database from raw data sources is often the premise of consequent applications. Automated construction, mining and reasoning of the knowledge bases have become possible as research advances in many related areas such as information extraction, natural language processing, data mining, search, machine learning, databases and data integration. The 1st Workshop on Knowledge Base Construction, Reasoning and Mining (KBCOM) is a new workshop that aims to gather together leading experts from industry and academia to share their visions about the field, discuss latest research results, and exchange exciting ideas. With a focus on invited talks and position papers, the workshop aims to provide a vivid forum of discussion about knowledge base-related research.

MIS2: Misinformation and Misbehavior Mining on the Web

Srijan Kumar (Stanford University), Meng Jiang (University of Notre Dame), Taeho Jung (University of Notre Dame), Roger Luo (Snap Research), Jure Leskovec (Stanford University)

Web is a space for all where people interact with each other and anyone can read, publish, and share content. While this has led to several groundbreaking benefits, it is also a breeding ground for misbehavior and misinformation. Anyone can reach thousands of people on the web instantaneously, say whatever they want, whenever they want, and yet be shielded by anonymity. This has led to increase of misbehavior and misinformation, such as harrassment, scams, spread of propaganda, hate speech, fake reviews, and many more. Study of this topic has become important among researchers across many subfields of the computational and social sciences, such as social network analysis, cybersecurity, human–computer interaction, linguistics, natural language processing, social psychology, sociology, political science, and cognitive science.

MIS2 is an interdisciplinary venue that invites researchers and practitioners that work on studying misbehavior and misinformation on the web. Web include social media, e-commerce platforms, collaborative and knowledge-based platforms (e.g., wikis and question-answer platforms like Quora, StackOverflow, etc.), computer mediated communications, both p2p (e.g., email, text chat, video chat, etc.) and broadcasting (e.g., discussion boards, video broadcast), online games, crowdsourcing platforms, and many more. Topics of interest include, but are not limited to, mining, understanding, modeling, detecting, predicting, preventing, and mitigating:

  • misbehavior and threat on the web, such as spam, trolling, scam, fraud, bots, coordinated attacks, cyberbullying, sockpuppets, propaganda, extremism, hate speech, and others.
  • false information on the web: fake reviews, fake news, rumors, fabricated images, videos, and others.

Learning from User Interactions

Emine Yilmaz Reader (University College London), Ahmed Hassan (Microsoft Research), Rishabh Mehrotra (University College London)
Search behavior, and information seeking behavior more generally, is often motivated by an underlying need or task, such as finding a bus schedule to plan travel, finding a recipe to make a dish for a potluck dinner, or finding the homepage of an author of a recently read book to see what other books she has published. While contemporary search engines are good at helping people resolve these types of look-up tasks, they are not as useful in helping people engaged in more complex tasks whose resolution might require multiple search sessions and multiple search strategies. Instead, search engines are optimized for particular types of tasks (e.g., look-up tasks and commerce tasks such as travel and shopping), for particular types of search behaviors (i.e., enter a query, review snippets, make a transaction) and for particular types of searchers (i.e., those who want to quickly find a single piece of information). Search engines are not optimized for tasks that require sustained interaction and engagement with information, the use of multiple, diverse search approaches to finding information or for searchers who want to cultivate a deeper, internalized understanding of a problem or topic. Contemporary search environments are tailored to support a small set of basic search tasks and provide searchers with few options to search and interact with information, and little to help them synthesize and integrate information across sessions. There is a gradual shift towards searching and presenting the information in a conversational form. Chatbots, personal assistants in our phones and eyes-free devices are being used increasingly more for different purposes, including information retrieval and exploration. With improved speech recognition and information retrieval systems, more and more users are increasingly relying on such digital assistants to fulfil their information needs and complete their tasks. Beyond traditional search environments, tasks help in providing an interpretable abstraction for grounding user interactions with such novel interfaces. Task-IR 2018 will be a highly interactive full day workshop that will provide a forum for academic and industrial researchers working at the intersection of search tasks, conversational IR and user interactions. The purpose is to provide an opportunity for people to present new work and early results, brainstorm different use cases, share best practices, and discuss the main challenges facing this line of research.

Workshop for WSDM Cup 2018: Music Recommendation and Churn Prediction Challenges

Yian Chen (KKBOX), Arden Chiu (KKBOX), Xing Xie (Mircosoft), Shou-De Lin (National Taiwan University)
Recommendation systems facilitate users retrieving contents they might like but not aware of yet. Furthermore, an effective recommendation system can potentially increase users’ retention and conversion rate. One critical challenge for building a recommender system lies in the existence of cold start cases when we have sparse records for certain users or items: without enough rating data about a new song or a new user, it is necessary to rely on auxiliary information to perform effective recommendation. In the first task of WSDM Cup 2018, we challenge the participants to solve the abovementioned challenges in building a music recommendation system. The 2nd task of the Cup focuses on churn prediction. For a subscription business, accurately predicting churn is critical to its long-term success as even a slight variation in churn can significantly affect the profits. In this task, participants are asked to build an algorithm that predicts whether a user will churn after their subscription expires. The competition data and award are provided by KKBOX, a leading music streaming service company from Taiwan. The competitions have attracted more than 1500 teams from all over the world to participate.