Programme
Welcome and Introduction
9:00-9:10: Welcome to the Making Sense of Microposts (#MSM2012) Workshop. Matthew Rowe; Milan Stankovic; Aba-Sah Dadzie
Keynote Talk
9:10 - 10:10: Greg Ver Steeg - Information Theoretic Tools for Social Media
abstractInformation theory provides a powerful set of tools for discovering relationships among variables with minimal assumptions. Social media platforms provide a rich source of information than can include temporal, spatial, textual, and network information. What are the interesting information theoretic measures for social media and how can we estimate these quantities? I will discuss how measures like information transfer can be used to quantify how predictive some variables are, e.g., how well one user's activity can predict another's. I will also discuss techniques for estimating entropies even when the data are sparse, as is the case for spatio-temporal events, or very high-dimensional, as is the case for textual information.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{steeg:2012,
author = {Greg Ver Steeg},
title = {Information Theoretic Tools for Social Media},
crossref = {proc_msm2012@www2012},
pages = {1--1},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
url = {http://ceur-ws.org/Vol-838/keynote_abstract.pdf},
}Session 1: Sentiment and Semantics
10:10 - 10:30: Small talk in the Digital Age: Making Sense of Phatic Posts. Danica Radovanovic; Massimo Ragnedda
abstract
This paper presents some practical implications of a theoretical web desktop analysis and addresses microposts in the Social Web contextual sense and their role contributing diverse information to the Web as part of informal and semi-formal communication and social activities on Social Networking Sites (SNS). We reflect upon and present the most pervasive and relevant socio-communication function of an online presence on microposts and social networks: the phatic communication function. Although some theorists such as Malinowski say these microposts have no practical information value, we argue that they have semantic and social value for the interlocutors, determined by socio-technological and cultural factors such as online presence and social awareness. We investigate and offer new implications for emerging social and communication dynamics formed around microposts, what we call here "phatic posts". We suggest that apparently trivial uses and features of SNS actually play an important role in setting the social and informational context of the rest of the conversation — a "phatic" function — and thus that these phatic posts are key to the success of SNS.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{radovanovic.ea:2012,
author = {Danica Radovanovic and Massimo Ragnedda},
title = {Small talk in the Digital Age: Making Sense of Phatic Posts},
crossref = {proc_msm2012@www2012},
pages = {10--13},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {social network sites, microposts, phatic posts, phatic communication, online communication, social dynamics},
url = {http://ceur-ws.org/Vol-838/paper_18.pdf},
}
10:30 – 11:00: Tea Break and posters/demos
11:00 - 11.30: Alleviating Data Sparsity for Twitter Sentiment Analysis. Hassan Saif; Yulan He; Harith Alani
abstract
Twitter has brought much attention recently as a hot research topic in the domain of sentiment analysis. Training sentiment classifiers from tweets data often faces the data sparsity problem partly due to the large variety of short and irregular forms introduced to tweets because of the 140-character limit. In this work we propose using two different sets of features to alleviate the data sparseness problem. One is the semantic feature set where we extract semantically hidden concepts from tweets and then incorporate them into classifier training through interpolation. Another is the sentiment-topic feature set where we extract latent topics and the associated topic sentiment from tweets, then augment the original feature space with these sentiment-topics. Experimental results on the Stanford Twitter Sentiment Dataset show that both feature sets outperform the baseline model using unigrams only. Moreover, using semantic features rivals the previously reported best result. Using sentiment-topic features achieves 86.3% sentiment classification accuracy, which outperforms existing approaches.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{saif.ea:2012,
author = {Hassan Saif and Yulan He and Harith Alani},
title = {Alleviating Data Sparsity for Twitter Sentiment Analysis},
crossref = {proc_msm2012@www2012},
pages = {2--9},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {Microblogs, Sentiment Analysis, Opinion Mining, Twitter, Semantic Smoothing, Data Sparsity},
url = {http://ceur-ws.org/Vol-838/paper_01.pdf},
}
11:30 - 11:50: Exploiting Twitter’s Collective Knowledge for Music Recommendations. Eva Zangerle; Wolfgang Gassler; Günther Specht
abstract
Twitter is the largest source of public opinion and also contains a vast amount of information about its users' music favors or listening behaviour. However, this source has not been exploited for the recommendation of music yet. In this paper, we present how Twitter can be facilitated for the creation of a data set upon which music recommendations can be computed. The data set is based on microposts which were automatically generated by music player software or posted by users and may also contain further information about audio tracks.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{zangerle.ea:2012,
author = {Exploiting Twitter's Collective Knowledge for Music Recommendations},
title = {Eva Zangerle and Wolfgang Gassler and G\"unther Specht},
crossref = {proc_msm2012@www2012},
pages = {14--17},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {Recommender Systems, Music Recommendation, Twitter},
url = {http://ceur-ws.org/Vol-838/paper_09.pdf},
}
Session 2: Information Extraction
11:50 - 12:00: Demo: Making Sense of Microposts at Scientific Conferences. Peter Kraker; Fleur Jeanquartier
abstract
Twitter is being widely used at scientific conferences. Following the microblogging stream, however, adds to the cognitive load of a conference participant. Therefore, there is a need for means of extracting the most important topics from a Twitter stream. This demo paper presents an adaptable system for detecting trends based on Twitter, and shows how it can be used within the setting of a conference. Following the cues of visual analytics, we use visualizations to show both the temporal evolution of topics, and the relations between different topics.
View online demo;
see also demo project page.
12:00 - 12:30: Extracting Unambiguous Keywords from Microposts Using Web and Query Logs Data. Davi de Castro Reis; Felipe Goldstein; Frederico Quintão
abstract
In the recent years, a new form of content type has become ubiquitous in the web. These are small and noisy text snippets, created by users of social networks such as Twitter and Facebook. The full interpretation of those microposts by machines impose tremendous challenges, since they strongly rely on context. In this paper we propose a task which is much simpler than full interpretation of microposts: we aim to build classification systems to detect keywords that unambiguously refer to a single dominant concept, even when taken out of context. For example, in the context of this task, apple would be classified as ambiguous whereas microsoft would not. The contribution of this work is twofold. First, we formalize this novel classification task that can be directly applied for extracting information from microposts. Second, we show how high precision classifiers for this problem can be built out of Web data and search engine logs, combining traditional information retrieval metrics, such as inverted document frequency, and new ones derived from search query logs. Finally, we have proposed and evaluated relevant applications for these classifiers, which were able to meet precision >= 72% and recall >= 56% on unambiguous keyword extraction from microposts. We also compare those results with closely related systems, none of which could outperform those numbers.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{castroReis.ea:2012,
author = {Davi de Castro Reis and Felipe Goldstein and Frederico Quint\~ao},
title = {Extracting Unambiguous Keywords from Microposts using Web and Query Logs Data},
crossref = {proc_msm2012@www2012},
pages = {18--25},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {unambiguity, word sense disambiguation, query logs, web, advertising},
url = {http://ceur-ws.org/Vol-838/paper_04.pdf},
}
12:30 - 14:00: Lunch
14:00 - 14:30: Knowledge Discovery in distributed Social Web sharing activities. Simon Scerri, Keith Cortis, Ismael Rivera, Siegfried Handschuh
abstract
Taking into consideration the steady shift towards information digitisation, an increasing number of approaches are targeting the unification of the user’s digital "Personal Information Sphere" to increase user awareness, provide single-point management, and enable context-driven recommendation. The Personal Information Sphere refers to both conventional information such as semi/structured information on the user’s personal devices and online accounts, but also in the form of more abstract personal information such as a user’s presence and activities. Online activities constitute a rich source for mining this type of personal information, since they are usually the only means by which a typical user consciously puts effort into sharing their activities. In view of this opportunity, we present an approach to extract implicit presence knowledge embedded in multiple streams of heterogeneous online posts. Semantic Web technologies are applied on top of syntactic analysis to extract and map entities onto a personal knowledge base, itself integrated within the wider context of the Semantic Web. For the purpose, we introduce the DLPO ontology — a concise ontology that captures all facets of dynamic personal information shared through online posts, as well their various derived links to personal and global semantic data clouds. Based on this conceptualisation, we outline the information extraction techniques targeted by our approach and present an as yet theoretical use-case to substantiate it.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{scerri.ea:2012,
author = {Simon Scerri and Keith Cortis and Ismael Rivera and Siegfried Handschuh},
title = {Knowledge Discovery in Distributed Social Web Sharing Activities},
crossref = {proc_msm2012@www2012},
pages = {26--33},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {Social Web, Microposts, Presence, Ontologies, Personal Information Management},
url = {http://ceur-ws.org/Vol-838/paper_17.pdf},
}
Session 3 Visualisation, Search and Networks
14:30 - 15:00: Visualizing Contextual and Dynamic Features of Microposts. Alexander Hubmann-Haidvogel; Adrian M. P. Brasoveanu; Arno Scharl; Marta Sabou; Stefan Gindl
abstract
Visual techniques provide an intuitive way of making sense of the large amounts of microposts available from social media sources, particularly in the case of emerging topics of interest to a global audience, which often raise controversy among key stakeholders. Micropost streams are context-dependent and highly dynamic in nature. We describe a visual analytics platform to handle high-volume micropost streams from multiple social media channels. For each post we extract key contextual features such as location, topic and sentiment, and subsequently render the resulting multi-dimensional information space using a suite of coordinated views that support a variety of complex information seeking behaviors. We also describe three new visualization techniques that extend the original platform to account for the dynamic nature of micropost streams through dynamic topography information landscapes, news flow diagrams and longitudinal cross-media analyses.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{hubmannHaidvogel.ea:2012,
author = {Alexander Hubmann-Haidvogel and Adrian M. P. Brasoveanu and Arno Scharl and Marta Sabou and Stefan Gindl},
title = {Visualizing Contextual and Dynamic Features of Micropost Streams},
crossref = {proc_msm2012@www2012},
pages = {34--40},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {Social Media Analytics, Microposts, Contextual Features, News Flow, Dynamic Visualization, Information Landscape},
url = {http://ceur-ws.org/Vol-838/paper_05.pdf},
}
15:00 - 15:30: When social bots attack: Modeling susceptibility of users in online social networks. Claudia Wagner; Silvia Mitter; Christian Körner; Markus Strohmaier
abstract
Social bots are automatic or semi-automatic computer programs that mimic humans and/or human behavior in online social networks. Social bots can attack users (targets) in on-line social networks to pursue a variety of latent goals, such as to spread information or to influence targets. Without a deep understanding of the nature of such attacks or the susceptibility of users, the potential of social media as an instrument for facilitating discourse or democratic processes is in jeopardy. In this paper, we study data from the Social Bot Challenge 2011 — an experiment conducted by the WebEcologyProject during 2011 — in which three teams implemented a number of social bots that aimed to influence user behavior on Twitter. Using this data, we aim to develop models to (i) identify susceptible users among a set of targets and (ii) predict users' level of susceptibility. We explore the predictiveness of three different groups of features (network, behavioral and linguistic features) for these tasks. Our results suggest that susceptible users tend to use Twitter for a conversational purpose and tend to be more open and social since they communicate with many different users, use more social words and show more affection than non-susceptible users.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{wagner.ea:2012,
author = {Claudia Wagner and Silvia Mitter and Christian K\"orner and Markus Strohmaier},
title = {When Social Bots Attack: Modeling Susceptibility of Users in Online Social Networks},
crossref = {proc_msm2012@www2012},
pages = {41--48},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {social bots, infection, user models},
url = {http://ceur-ws.org/Vol-838/paper_11.pdf},
}
15:30 - 16:00: Tea Break and posters/demos
16:00 - 16:30: What makes a tweet relevant for a topic? Ke Tao; Fabian Abel; Claudia Hauff; Geert-Jan Houben
abstract
Users who rely on microblogging search (MS) engines to find relevant microposts for their queries usually follow their interests and rationale when deciding whether a retrieved post is of interest to them or not. While today's MS engines commonly rely on keyword-based retrieval strategies, we investigate if there exist additional micropost characteristics that are more predictive of a post's relevance and interestingness than its keyword-based similarity with the query. In this paper, we experiment with a corpus of Twitter messages and investigate sixteen features along two dimensions: topic-dependent and topic-independent features. Our in-depth analysis compares the importance of the different types of features and reveals that semantic features and therefore an understanding of the semantic meaning of the tweets plays a major role in determining the relevance of a tweet with respect to a query. We evaluate our findings in a relevance classification experiment and show that by combining different features, we can achieve a precision and recall of more than 35% and 45% respectively.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{tao.ea:2012,
author = {Ke Tao and Fabian Abel and Claudia Hauff and Geert-Jan Houben},
title = {What Makes a Tweet Relevant for a Topic?},
crossref = {proc_msm2012@www2012},
pages = {49--56},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {twitter, relevance, analysis, search, features},
url = {http://ceur-ws.org/Vol-838/paper_08.pdf},
}
16:30 - 17:00: Understanding co-evolution of social and content networks on Twitter. Philipp Singer; Claudia Wagner; Markus Strohmaier
abstract
Social media has become an integral part of today's web and allows users to share content and socialize. Understanding the factors that influence how users evolve over time — for example how their social network and their contents co-evolve — is an issue of both theoretical and practical relevance. This paper sets out to study the temporal co-evolution of content and social networks on Twitter and bi-directional influences between them by using multilevel time series regression models. Our findings suggest that on Twitter social networks have a strong influence on content networks over time, and that social network properties, such as users' number of followers, strongly influence how active and informative users are. While our investigations are limited to one small dataset obtained from Twitter, our analysis opens up a path towards more systematic studies of network co-evolution on platforms such as Twitter or Facebook. Our results are relevant for researchers and social media hosts interested in understanding how content-related and social activities of social media users evolve over time and which factors impact their co-evolution.
bibtex
@Proceedings{proc_msm2012@www2012,
title = {Proceedings, 2nd Workshop on Making Sense of Microposts {(\#MSM2012)}: Big things come in small packages, Lyon, France, 16 April 2012},
year = 2012,
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
month = {April},
url = {http://ceur-ws.org/Vol-838},
}
@InProceedings{singer.ea:2012,
author = {Philipp Singer and Claudia Wagner and Markus Strohmaier},
title = {Understanding Co-evolution of Social and Content Networks on Twitter},
crossref = {proc_msm2012@www2012},
pages = {57--60},
booktitle = {Making Sense of Microposts {(\#MSM2012)}},
year = 2012,
keywords = {Microblog, Twitter, Influence Patterns, Semantic Analysis, Time Series},
url = {http://ceur-ws.org/Vol-838/paper_10.pdf},
}
Workshop Closing
17:00 - 17:30: Discussion/Panel
17:30 - 17:45: Awards