Detecting events using social media such as Twitter has many useful applications in real-life situations. Many algorithms which all use different information sources---either textual, temporal, geographic or community features---have been developed to achieve this task. Semantic information is often added at the end of the event detection to classify events into semantic topics. But semantic information can also be used to drive the actual event detection, which is less covered by academic research. We therefore supplemented an existing baseline event clustering algorithm with semantic information about the tweets in order to improve its performance. This paper lays out the details of the semantics-driven event clustering algorithms developed, discusses a novel method to aid in the creation of a ground truth for event detection purposes, and analyses how well the algorithms improve over baseline. We find that assigning semantic information to every individual tweet results in just a worse performance in $F_1$ measure compared to baseline. If however semantics are assigned on a coarser, hashtag level the improvement over baseline is substantial and significant in both precision and recall.

                            
@InProceedings{microposts2015_deBoom.ea:2015,
  author = {De Boom, Cedric and Van Canneyt, Steven and Dhoedt, Bart},
  title = {Semantics-driven Event Clustering in {T}witter Feeds},
  crossref = {proc_microposts2015@www2015},
  pages = {2--9},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Detecting events using social media such as Twitter has many useful applications in real-life situations. Many algorithms which all use different information sources---either textual, temporal, geographic or community features---have been developed to achieve this task. Semantic information is often added at the end of the event detection to classify events into semantic topics. But semantic information can also be used to drive the actual event detection, which is less covered by academic research. We therefore supplemented an existing baseline event clustering algorithm with semantic information about the tweets in order to improve its performance. This paper lays out the details of the semantics-driven event clustering algorithms developed, discusses a novel method to aid in the creation of a ground truth for event detection purposes, and analyses how well the algorithms improve over baseline. We find that assigning semantic information to every individual tweet results in just a worse performance in $F_1$ measure compared to baseline. If however semantics are assigned on a coarser, hashtag level the improvement over baseline is substantial and significant in both precision and recall.},
  keywords = {Semantic information, event detection, clustering, social media, Twitter},
  url = {http://ceur-ws.org/Vol-1395/paper_02.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                    

Social spam produces a great amount of noise on social media services such as Twitter, which reduces the signal-to-noise ratio that both end users and data mining applications observe. Existing techniques on social spam detection have focused primarily on the identification of spam accounts by using extensive historical and network-based data. In this paper we focus on the detection of spam tweets, which optimises the amount of data that needs to be gathered by relying only on tweet-inherent features. This enables the application of the spam detection system to a large set of tweets in a timely fashion, potentially applicable in a real-time or near real-time setting. Using two large hand-labelled datasets of tweets containing spam, we study the suitability of five classification algorithms and four different feature sets to the social spam detection task. Our results show that, by using the limited set of features readily available in a tweet, we can achieve encouraging results which are competitive when compared against existing spammer detection systems that make use of additional, costly user features. Our study is the first that attempts at generalising conclusions on the optimal classifiers and sets of features for social spam detection over different datasets.

                            
@InProceedings{{microposts2015_wang.ea:2015,
  author = {Wang, Bo and Zubiaga, Arkaitz and Liakata, Maria and Procter, Rob},
  title = {Making the Most of Tweet-Inherent Features for Social Spam Detection on {T}witter},
  crossref = {proc_microposts2015@www2015},
  pages = {10--16},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Social spam produces a great amount of noise on social media services such as Twitter, which reduces the signal-to-noise ratio that both end users and data mining applications observe. Existing techniques on social spam detection have focused primarily on the identification of spam accounts by using extensive historical and network-based data. In this paper we focus on the detection of spam tweets, which optimises the amount of data that needs to be gathered by relying only on tweet-inherent features. This enables the application of the spam detection system to a large set of tweets in a timely fashion, potentially applicable in a real-time or near real-time setting. Using two large hand-labelled datasets of tweets containing spam, we study the suitability of five classification algorithms and four different feature sets to the social spam detection task. Our results show that, by using the limited set of features readily available in a tweet, we can achieve encouraging results which are competitive when compared against existing spammer detection systems that make use of additional, costly user features. Our study is the first that attempts at generalising conclusions on the optimal classifiers and sets of features for social spam detection over different datasets.},
  keywords = {spam detection, classification, social media, microblogging},
  url = {http://ceur-ws.org/Vol-1395/paper_07.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                        

Twitter has become a viable platform for spammers, who often form networks to further their reach. Troublesomely, targeted users become increasingly frustrated, or worse, view content resulting in computer virus infection. We build on previous work around detecting spam on Twitter, proposing that subcategorising spammers can increase our understanding of their connections in spammer networks and aid detection. After defining five subcategories of spammers and classifying users accordingly, correlations between the categories of spammers and the categories of their followers and followees are explored. We also find that all spam subcategories follow a higher share of non-spam accounts than any individual spam subcategories, and, unexpectedly, that every spammer subcategory is followed by non-spammers more than by individual counterparts.

                          
@InProceedings{microposts2015_edwards.ea:2015,
  author = {Edwards, Gordon and Guy, Amy},
  title = {Connections between {T}witter Spammer Categories},
  crossref = {proc_microposts2015@www2015},
  pages = {22--25},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Twitter has become a viable platform for spammers, who often form networks to further their reach. Troublesomely, targeted users become increasingly frustrated, or worse, view content resulting in computer virus infection. We build on previous work around detecting spam on Twitter, proposing that subcategorising spammers can increase our understanding of their connections in spammer networks and aid detection. After defining five subcategories of spammers and classifying users accordingly, correlations between the categories of spammers and the categories of their followers and followees are explored. We also find that all spam subcategories follow a higher share of non-spam accounts than any individual spam subcategories, and, unexpectedly, that every spammer subcategory is followed by non-spammers more than by individual counterparts.},
  keywords = {Twitter, spammer categories, spam, social media, microposts, machine learning},
  url = {http://ceur-ws.org/Vol-1395/paper_11.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                      

Following a shooting attack by two self-proclaimed Islamist gunmen at the offices of French satirical weekly Charlie Hebdo on 7th January 2015, there emerged the hashtag #JeSuisCharlie on Twitter as an expression of condolences for the victims, solidarity, and support for the magazine's right to free speech. Almost simultaneously, however, there was also #JeNeSuisPasCharlie explicitly countering the former, affirmative hashtag. In this paper, we analyse 74,047 tweets containing #JeNeSuisPasCharlie posted between 7th and 11th January. Our network analysis and semantic cluster analysis of those 74,047 tweets reveal that the hashtag in question constitutes a form of resistance to the mainstream framing of the issue as freedom of expression being threatened by religious intolerance and violence. The resistance was manifested through three phases: sharing condolences but indicating a reservation against the mainstream frame (Grief); voicing out resistance against the frame (Resistance); and developing and deploying alternative frames such as hate speech, Eurocentrism, and Islamophobia (Alternatives). The hashtag in this context served as a vehicle through which users formed, enhanced, and declared their self-identity.

@InProceedings{microposts2015_socsci_giglietto.ea:2015,
  author = {Giglietto, Fabio and Lee, Yenn},
  title = {{To Be or Not to Be Charlie}: {T}witter Hashtags as a Discourse and Counter-discourse in the Aftermath of the 2015 {Charlie Hebdo} Shooting in {F}rance},
  crossref = {proc_microposts2015@www2015},
  pages = {33--37},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Following a shooting attack by two self-proclaimed Islamist gunmen at the offices of French satirical weekly Charlie Hebdo on 7th January 2015, there emerged the hashtag #JeSuisCharlie on Twitter as an expression of condolences for the victims, solidarity, and support for the magazine's right to free speech. Almost simultaneously, however, there was also #JeNeSuisPasCharlie explicitly countering the former, affirmative hashtag. In this paper, we analyse 74,047 tweets containing #JeNeSuisPasCharlie posted between 7th and 11th January. Our network analysis and semantic cluster analysis of those 74,047 tweets reveal that the hashtag in question constitutes a form of resistance to the mainstream framing of the issue as freedom of expression being threatened by religious intolerance and violence. The resistance was manifested through three phases: sharing condolences but indicating a reservation against the mainstream frame (Grief); voicing out resistance against the frame (Resistance); and developing and deploying alternative frames such as hate speech, Eurocentrism, and Islamophobia (Alternatives). The hashtag in this context served as a vehicle through which users formed, enhanced, and declared their self-identity.},
  keywords = {counter-discourse, freedom of expression, hashtag, identity, semantic cluster analysis},
  url = {http://ceur-ws.org/Vol-1395/paper_12.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                        

In the ordinary debate about the political culture decline, social networks have recently changed the social scenario, showing its relevance in down-up social movements. Therefore, social networks are taken here as a potential place for the existence of active citizens - ones that are able and keen about political action in a common world or community. Such recent political revitalization demonstrates the relevance of understanding net activism as a precondition for an active citizenship in the digital culture, where new forms of communication and social interaction seem to influence the democratic relationships in ICT mediated public spheres. The main objective of this article is to present a research design for the identification of elements that promote social empowerment in digital culture. It proposes research procedures for the study of political net activist groups in social networks. Methods, instruments and resources were created and articulated for the collection and treatment of big data and for further qualitative analysis of content, by successive steps of data mining. In addition to contributing to the internet studies field, by proposing a qualitative investigation of social networks, this research design also brings innovation to the Education field as the results of the application of this research design (the identification of important elements for citizens' empowerment) will be used to ground the development of guidelines to teachers and to teachers' education on critical appropriation of social networks in active citizens' education.

                            
@InProceedings{microposts2015_socsci_coelho.ea:2015,
  author = {Coelho, Isabel Colucci and Lapa, Andrea and Ramos, Vinicius and Malini, Fabio},
  title = {A Research Design for the Analysis of Contemporary Social Movements},
  crossref = {proc_microposts2015@www2015},
  pages = {38--42},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {In the ordinary debate about the political culture decline, social networks have recently changed the social scenario, showing its relevance in down-up social movements. Therefore, social networks are taken here as a potential place for the existence of active citizens -- ones that are able and keen about political action in a common world or community. Such recent political revitalization demonstrates the relevance of understanding net activism as a precondition for an active citizenship in the digital culture, where new forms of communication and social interaction seem to influence the democratic relationships in ICT mediated public spheres. The main objective of this article is to present a research design for the identification of elements that promote social empowerment in digital culture. It proposes research procedures for the study of political net activist groups in social networks. Methods, instruments and resources were created and articulated for the collection and treatment of big data and for further qualitative analysis of content, by successive steps of data mining. In addition to contributing to the internet studies field, by proposing a qualitative investigation of social networks, this research design also brings innovation to the Education field as the results of the application of this research design (the identification of important elements for citizens' empowerment) will be used to ground the development of guidelines to teachers and to teachers' education on critical appropriation of social networks in active citizens' education.},
  keywords = {quali-quanti methodology; social network analysis; citizen's education; digital culture; net activism},
  url = {http://ceur-ws.org/Vol-1395/paper_14.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                        

Considering wide use of Twitter as the source of information, reaching an interesting tweet for a user among a bunch of tweets is challenging. In this work we propose a Named Entity Recognition (NER) based user profile modeling for Twitter users and employ this model to generate personalized tweet recommendations. Effectiveness of the proposed method is shown through a set of experiments.

                    
@InProceedings{microposts2015_karatay.ea:2015,
  author = {Karatay, Deniz and Karagoz Pinar},
  title = {User Interest Modeling in {T}witter with Named Entity Recognition},
  crossref = {proc_microposts2015@www2015},
  pages = {17--20},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Considering wide use of Twitter as the source of information, reaching an interesting tweet for a user among a bunch of tweets is challenging. In this work we propose a Named Entity Recognition (NER) based user profile modeling for Twitter users and employ this model to generate personalized tweet recommendations. Effectiveness of the proposed method is shown through a set of experiments.},
  keywords = {Named Entity Recognition, Tweet Segmentation, Tweet Classification, Tweet Ranking, Tweet Recommendation},
  url = {http://ceur-ws.org/Vol-1395/paper_03.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                    

Research shows that microblogging websites such as Tumblr are being misused as a platform to disseminate hate and extremism. We formulate the problem of locating such extremist communities as a graph search problem. We propose a topical crawler based approach performing several tasks: searching for a blogger, computing its similarity against exemplary documents, filtering hate promoting bloggers, navigating through links to other bloggers and managing a queue of such bloggers for social network analysis. We conduct experiments on real world dataset and examine the effectiveness of 'like' and 'reblog' features as links between bloggers. Experimental results demonstrates that the proposed solution approach is effective with an F-score of $0.80$.

                            
@InProceedings{{microposts2015_agarwal.ea:2015,
  author = {Agarwal, Swati and Sureka, Ashish},
  title = {A Topical Crawler for Uncovering Hidden Communities of Extremist Micro-Bloggers on {Tumblr}},
  crossref = {proc_microposts2015@www2015},
  pages = {26--27},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {Research shows that microblogging websites such as Tumblr are being misused as a platform to disseminate hate and extremism. We formulate the problem of locating such extremist communities as a graph search problem. We propose a topical crawler based approach performing several tasks: searching for a blogger, computing its similarity against exemplary documents, filtering hate promoting bloggers, navigating through links to other bloggers and managing a queue of such bloggers for social network analysis. We conduct experiments on real world dataset and examine the effectiveness of 'like' and 'reblog' features as links between bloggers. Experimental results demonstrates that the proposed solution approach is effective with an F-score of $0.80$.},
  keywords = {Mining User Generated Content, Online Radicalization, Social Media Analytics},
  url = {http://ceur-ws.org/Vol-1395/paper_04.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
                        

We present a novel approach for detecting, classifying, and linking entities from Twitter posts (tweets). The task is challenging because of the noisy, short, and informal nature of tweets. Consequently, the proposed approach introduces several methods that robustly facilitate successful realization of the task with enhanced performance in several measures.

                  
@InProceedings{microposts2015_neel_yamada.ea:2015,
  author = {Yamada, Ikuya and Takeda, Hideaki and Takefuji, Yoshiyasu},
  title = {An End-to-End Entity Linking Approach for Tweets},
  crossref = {proc_microposts2015@www2015},
  pages = {55--56},
  booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
  year = 2015,
  abstract = {We present a novel approach for detecting, classifying, and linking entities from Twitter posts (tweets). The task is challenging because of the \textit{noisy}, \textit{short}, and \textit{informal} nature of tweets. Consequently, the proposed approach introduces several methods that robustly facilitate successful realization of the task with enhanced performance in several measures.},
  keywords = {Entity linking; Wikification; Twitter; DBpedia; Wikipedia},
  url = {http://ceur-ws.org/Vol-1395/paper_16.pdf},
}

@Proceedings{proc_microposts2015@www2015,
  title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
  year = 2015,
  booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
  editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
  url = {http://ceur-ws.org/Vol-1395},
}
              

In this paper we present an approach for extracting and linking entities from short and noisy microblog posts. We describe a diverse set of approaches based on the Semanticizer, an open-source entity linking framework developed at the University of Amsterdam, adapted to the task of the #Microposts2015 challenge. We consider alternatives for dealing with ambiguity that can help in the named entity extraction and linking processes. We retrieve entity candidates from multiple sources and process them in a four-step pipeline. Results show that we correctly manage to identify entity mentions (our best run attains an F1 score of 0.809 in terms of the strong mention match metric), but subsequent steps prove to be more challenging for our approach.

                    
@InProceedings{microposts2015_neel_garbacea.ea:2015,
    author = {G\^arbacea, Cristina and Odijk, Daan and Graus, David and Sijaranamual, Isaac and {de Rijke}, Maarten},
    title = {Combining Multiple Signals for Semanticizing Tweets: {U}niversity of {A}msterdam at \#{M}icroposts2015},
    crossref = {proc_microposts2015@www2015},
    pages = {59--60},
    booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
    year = 2015,
    abstract = {In this paper we present an approach for extracting and linking entities from short and noisy microblog posts. We describe a diverse set of approaches based on the Semanticizer, an open-source entity linking framework developed at the University of Amsterdam, adapted to the task of the \#Microposts2015 challenge. We consider alternatives for dealing with ambiguity that can help in the named entity extraction and linking processes. We retrieve entity candidates from multiple sources and process them in a four-step pipeline. Results show that we correctly manage to identify entity mentions (our best run attains an F1 score of 0.809 in terms of the strong mention match metric), but subsequent steps prove to be more challenging for our approach. },
    keywords = {Named entity extraction; Named entity linking; Social media},
    url = {http://ceur-ws.org/Vol-1395/paper_17.pdf},
}

@Proceedings{proc_microposts2015@www2015,
    title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
    year = 2015,
    booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
    editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
    url = {http://ceur-ws.org/Vol-1395},
}
                

A short text gets updated every now and then. With the global upswing of such micro posts, the need to retrieve in- formation from them also seems to be incumbent. This work focuses on the knowledge extraction from the micro posts by having entity as evidence. Here the extracted entities are then linked to their relevant DBpedia source by featurization, Part Of Speech (POS) tagging, Named Entity Recognition (NER) and Word Sense Disambiguation (WSD). This short paper encompasses its contribution to #Microposts2015 - NEEL task by experimenting existing Machine Learning (ML) algorithms.

                    
@InProceedings{microposts2015_neel_barathi.ea:2015,
    author = {{H B}, Barathi Ganesh and {N}, Abinaya and {M}, Anand Kumar and {R}, Vinaykumar and {K P}, Soman},
    title = {{AMRITA -- CEN@NEEL}: Identification and Linking of {T}witter Entities},
    crossref = {proc_microposts2015@www2015},
    pages = {64--65},
    booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
    year = 2015,
    abstract = {A short text gets updated every now and then. With the global upswing of such micro posts, the need to retrieve information from them also seems to be incumbent. This work focuses on the knowledge extraction from the micro posts by having entity as evidence. Here the extracted entities are then linked to their relevant DBpedia source by featurization, Part Of Speech (POS) tagging, Named Entity Recognition (NER) and Word Sense Disambiguation (WSD). This short paper encompasses its contribution to \#Micropost2015 - NEEL task by experimenting existing Machine Learning (ML) algorithms.},
    keywords = {CRF, Micro posts, NER},
    url = {http://ceur-ws.org/Vol-1395/paper_20.pdf},
}

@Proceedings{proc_microposts2015@www2015,
    title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
    year = 2015,
    booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
    editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
    url = {http://ceur-ws.org/Vol-1395},
}
                

This paper presents our system at the #Microposts2015 NEEL Challenge. The task is to recognize and type mentions from English Microposts, and link them to their corresponding entries in DBpedia 2014. For this task, we developed a method based on a state-of-the-art entity linking system - REL-RW~\cite{DBLP:conf/cikm/GuoB14}, which exploits the entity graph from the knowledge base to compute semantic relatedness between entities, and use it for entity disambiguation. The advantage of the approach is its robustness for various types of documents. We built our system on REL-RW and employed a tweet specific NER component to improve the performance on tweets. The system achieved overall 0.35 F1 on the development dataset from NEEL 2015, while the disambiguation component alone can achieve 0.70 F1.

                    
@InProceedings{microposts2015_neel_guo.ea:2015,
    author = {Guo, Zhaochen and Barbosa, Denilson},
    title = {Entity Recognition and Linking on Tweets with Random Walks},
    crossref = {proc_microposts2015@www2015},
    pages = {57--58},
    booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
    year = 2015,
    abstract = {This paper presents our system at the \#Microposts2015 NEEL Challeng [4]. The task is to recognize and type mentions from English Microposts, and link them to their corresponding entries in DBpedia 2014. For this task, we developed a method based on a state-of-the-art entity linking system - REL-RW [2], which exploits the entity graph from the knowledge base to compute semantic relatedness between entities, and use it for entity disambiguation. The advantage of the approach is its robustness for various types of documents. We built our system on REL-RW and employed a tweet specific NER component to improve the performance on tweets. The system achieved overall 0.35 F1 on the development dataset from NEEL 2015, while the disambiguation component alone can achieve 0.70 F1.},
    keywords = {Entity Recognition, Entity Disambiguation, Social Media},
    url = {http://ceur-ws.org/Vol-1395/paper_21.pdf},
}

@Proceedings{proc_microposts2015@www2015,
    title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
    year = 2015,
    booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
    editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
    url = {http://ceur-ws.org/Vol-1395},
}
                

The task of Named Entity Extraction and Linking (NEEL) challange 2015 is considered as two successive tasks : Named Entity Extraction (NEE) from the tweets and Named En- tity Linking (NEL) with DBPedia. For NEE task we use CRF++ [1] to create a language model on the given train-ing data. For entity linking, we use DBPedia spotlight.

                    
@InProceedings{microposts2015_neel_sinha.ea:2015,
    author = {Sinha, Priyanka and Barik, Biswanath},
    title = {Named Entity Extraction and Linking in \#{M}icroposts},
    crossref = {proc_microposts2015@www2015},
    pages = {66--67},
    booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
    year = 2015,
    abstract = {The task of Named Entity Extraction and Linking (NEEL) challange 2015 [5] is considered as two successive tasks : Named Entity Extraction (NEE) from the tweets and Named Entity Linking (NEL) with DBpedia. For NEE task we use CRF++ [1] to create a language model on the given training data. For entity linking, we use DBpedia Spotlight.},
    keywords = {Twitter, Entity, Linking, Social Media, DBpedia},
    url = {http://ceur-ws.org/Vol-1395/paper_19.pdf},
}

@Proceedings{proc_microposts2015@www2015,
    title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
    year = 2015,
    booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
    editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
    url = {http://ceur-ws.org/Vol-1395},
                    }
                

This paper describes the participation of the UNIBA team in the Named Entity rEcognition and Linking (NEEL) Challenge. We propose a knowledge-based algorithm able to recognize and link named entities in English tweets.The approach combines the simple Lesk algorithm with information coming from both a distributional semantic model and usage frequency of Wikipedia concepts. The algorithm performs poorly in the entity recognition, while it achieves good results in the disambiguation step.

@InProceedings{microposts2015_neel_basile.ea:2015,
    author = {Basile, Pierpaolo and Caputo, Annalina  and Semeraro, Giovanni and Narducci, Fedelucio},
    title = {{UNIBA}: Exploiting a Distributional Semantic Model for Disambiguating and Linking Entities in Tweets},
    crossref = {proc_microposts2015@www2015},
    pages = {62--63},
    booktitle = {5th Workshop on Making Sense of Microposts {(\#Microposts2015)}},
    year = 2015,
    abstract = {This paper describes the participation of the UNIBA team in the Named Entity rEcognition and Linking (NEEL) Challenge. We propose a knowledge-based algorithm able to recognize and link named entities in English tweets.The approach combines the simple Lesk algorithm with information coming from both a distributional semantic model and usage frequency of Wikipedia concepts. The algorithm performs poorly in the entity recognition, while it achieves good results in the disambiguation step.},
    keywords = {Named Entity Linking, Distributional Semantic Models, Lesk Algorithm},
    url = {http://ceur-ws.org/Vol-1395/paper_15.pdf},
}

@Proceedings{proc_microposts2015@www2015,
    title = {Proceedings, 5th Workshop on Making Sense of Microposts {(\#Microposts2015)}: Big things come in small packages, Florence, Italy, 18th of May 2015},
    year = 2015,
    booktitle = {Making Sense of Microposts {(\#Microposts2015)}},
    editor = {Matthew Rowe and Milan Stankovic and Aba-Sah Dadzie},
    url = {http://ceur-ws.org/Vol-1395},
}