Information Retrieval by Semantically Grouping Search Query Data
by Wim Florijn
Query data analysis is a time-consuming task. Currently, a method exists where word (combinations) in queries are labelled by using an information collection consisting of regular expressions. Because the information collection does not contain regular expressions from never-before seen domains, the method heavily relies on manual work, resulting in decreased scalibility. Therefore, a machine-learning based method is proposed in order to automate the annotation of word (combinations) in queries. This research searches for the optimal configuration of a pre-processing method, word embedding model, additional data set and classifier variant. All configurations have been examined on multiple data sets, and appropriate performance metrics have been calculated. The results show that the optimal configuration consists of omitting pre-processing, training a fastText model and enriching word features using additional data in combination with a recurrent classifier. We found that an approach using machine learning is able to obtain excellent performance on the task of labelling word (combinations) in search queries.
by Anna Priante
Social movement organizations widely use social media to organize collective action for social change, such as cancer awareness campaigns. However, little is known about how effective online social movement campaigns are at generating social change by translating online action into meaningful (offline) action. This dissertation examines the micro-mobilization dynamics at play that can explain the effectiveness of online social social movement campaigns. This book comprises seven chapters presenting research based on a multidisciplinary, mixed-method approach, combining theories and methods from sociology, social psychology, communication science, and computational social science. The findings show that, with mobilization dynamics of collective action, we can gain an important understanding of the mechanisms at work during online social movement campaigns and of the effectiveness of such campaigns in fostering communication processes related to the cause, obtaining important resources for the cause, developing a collective identity, and raising awareness.
Anna’s defense was the 5000th PhD defense at the UT!
Responses to HPV Vaccination Campaigns in The Netherlands: an analysis of discussions on Twitter
by Marieke Graef
Even though the human papillomavirus vaccine (HPV) is an effective and safe instrument to decrease HPV infections and cases of several types of cancer, the Dutch HPV vaccination rate has been suboptimal from the start and has even shown a decline in the last two years. This study sought to assess the determinants of HPV vaccination uptake in the Netherlands and how the vaccine and RIVM and GGDTwente messages were discussed on Twitter from 2011 till 2016. Method: All Dutch language tweets mentioning HPV from the years 2011 till 2016 were collected from a database, amounting to a total of 17319. A content analysis of all tweets was carried out manually. The content of the GGDTwente and RIVM tweets was examined as well as responses to these tweets. Furthermore, the tweets were analyzed for specific determinants of HPV vaccination uptake and general sentiments. Results: The GGDTwente and RIVM only became truly active on Twitter regarding the HPV vaccination program in 2015. The RIVM tweets received significantly more response, though this response mostly consisted of retweets. Nearly all GGDTwente tweets concerned vaccination schedules. By far the most common determinant of low vaccination uptake in tweets from the public was the fear of side-effects, with scare stories going viral in 2015 and 2016 especially. On the other hand, publications on the high number of HPV infections among women received a lot of attention as well. Overall, the general sentiment towards the HPV vaccine on Twitter was more positive than negative in the first years, but due to stories about side-effects turned more negative in 2015. Conclusions: The results show that the fear of side-effects is something that needs to be addressed by public health authorities. Additionally, more practical measures such as a school-based vaccination program may be a great way to help increase the vaccination rate.
(a thread on Mastodon U. Twente)
I signed the Klimaatbrief Universiteiten. Our university does not have an ambitious climate agenda. A common approach among universities is lacking. With this letter, we call upon university management to develop and implement policies to drastically reduce the universities’ carbon emissions.
Frankly speaking, the policies that this letter calls for should not be controversial at all. Universities have a moral duty to work on the big problems of the world, and a duty to advance approaches that may solve these problems. In fact, the University of Twente can build a campus that is CO2 neutral now. Let me give a few examples.
Let’s build, on campus, the state-of-the-art wind mills that use generators developed at the University of Twente. The superconductors developed by Marc Dhallé and colleagues, Lighter windmills thanks to superconductivity, replace the heavy magnets inside the generators of conventional wind mills. As a result, the weight and size of the new generator is significantly reduced while at the same time, it is capable of delivering the same output power. Another advantage is the minimal use of rare earth metals.
Let’s put solar panels on every roof and turn everyday objects on campus into solar panels using luminescent solar concentrator (LSC) photovoltaic technologies that Angèle Reinders and colleagues experiment with. The typical material properties of LSCs — low cost, colorful, bendable, and transparency — offer a lot of design freedom.
Let’s use the additional energy generated on campus to generate solar fuels. This involves the direct conversion of energy from sunlight into a usable fuel (in this case, hydrogen). Using only earth-abundant materials, Han Gardeniers, Jurriaan Huskens and colleagues developed the most efficient conversion method to date: UT boosts efficiency of solar fuels.
The high school children that are on strike for the climate now will be our future students. Let’s give them the world — and the campus — they protested for.
Temporal Information Models for Real-Time Microblog Search
by Flávio Martins
Real-time search in Twitter and other social media services is often biased towards the most recent results due to the “in the moment” nature of topic trends and their ephemeral relevance to users and media in general. However, “in the moment”, it is often difficult to look at all emerging topics and single-out the important ones from the rest of the social media chatter. This thesis proposes to leverage on external sources to estimate the duration and burstiness of live Twitter topics. It extends preliminary research where it was shown that temporal re-ranking using external sources could indeed improve the accuracy of results. To further explore this topic we pursued three significant novel approaches:
(1) multi-source information analysis that explores behavioral dynamics of users, such as Wikipedia live edits and page view streams, to detect topic trends and estimate the topic interest over time;
(2) efficient methods for federated query expansion towards the improvement of query meaning; and
(3) exploiting multiple sources towards the detection of temporal query intent.
It differs from past approaches in the sense that it will work over real-time queries, leveraging on live user-generated content. This approach contrasts with previous methods that require an offline preprocessing step.
(Photo by @email@example.com)
Recommending Users: Whom to Follow on Federated Social Networks
by Jan Trienes, Andrés Torres Cano, and Djoerd Hiemstra
To foster an active and engaged community, social networks employ recommendation algorithms that filter large amounts of contents and provide a user with personalized views of the network. Popular social networks such as Facebook and Twitter generate follow recommendations by listing profiles a user may be interested to connect with. Federated social networks aim to resolve issues associated with the popular social networks – such as large-scale user-surveillance and the miss-use of user data to manipulate elections – by decentralizing authority and promoting privacy. Due to their recent emergence, recommender systems do not exist for federated social networks, yet. To make these networks more attractive and promote community building, we investigate how recommendation algorithms can be applied to decentralized social networks. We present an offline and online evaluation of two recommendation strategies: a collaborative filtering recommender based on BM25 and a topology-based recommender using personalized PageRank. Our experiments on a large unbiased sample of the federated social network Mastodon shows that collaborative filtering approaches outperform a topology-based approach, whereas both approaches significantly outperform a random recommender. A subsequent live user experiment on Mastodon using balanced interleaving shows that the collaborative filtering recommender performs on par with the topology-based recommender.
This paper will be presented at the 17th Dutch-Belgian Information Retrieval workshop in Leiden on 23 November 2018
The The 17th Dutch-Belgian Information Retrieval workshop (DIR 2018) takes place in Leiden on 23 November 2018. DIR has a diverse 1-day programme with 2 keynotes, 5 talks, 7 posters and 4 demos!
The Dutch-Belgian Information Retrieval workshop (DIR) aims to serve as an international platform (with a special focus on the Netherlands and Belgium) for exchange and discussions on research & applications in the field of information retrieval and related fields.
More information at: http://dir2018.nl.
The European Conference on Information Retrieval (ECIR) is the prime European forum for the presentation of original research in the field of Information Retrieval. ECIR 2019 is seeking high-quality and original submissions on theory, experimentation, and practice regarding the retrieval, representation, management, and usage of textual, visual and multi-modal information. ECIR strongly supports user, system, application, and evaluation focused papers:
- User aspects including information interaction, contextualisation, personalisation, simulation, characterisation, and information behaviours.
- System aspects including retrieval and recommendation algorithms, machine learning, deep learning, content representation, natural language processing, system architectures, and efficiency methods.
- Applications such as search and recommender systems, web and social media apps, domain specific search (professional, bio, chem, etc.), novel interfaces, intelligent search agents/bots, and related innovative search tools.
- Evaluation research including new measures and novel methods for the measurement and evaluation of users, systems and/or applications.
In addition to these traditional topic areas, ECIR 2019 will be encouraging the submissions of papers on:
- New and Emerging Applications of IR including eHealth, precision medicine, early risk prediction, incident streams, digital text forensics, cultural and social informatics, life and biodiversity retrieval, living lab evaluations, conversational and intelligent search agents, and search as learning.
The Short Paper Track calls for original contributions presenting novel, thought-provoking ideas and addressing innovative application areas within the field of Information Retrieval. The inclusion of promising (preliminary) results is encouraged but not required. Papers that stimulate and promote discussion are particularly encouraged. Short paper submissions should be 6 pages in length plus additional pages for references.
Understanding engagement behavior in online brand communities : how social identity relates to frequency of interaction and tweet sentiment.
by Candy Reebroek
This study explains engagement behavior in online brand communities based on data of Twitter users who present different types of social identities. For this, we examined fifteen online brand communities that are popular on Twitter and originated from fashion, fast-food, gaming, cars, and sports sectors. In total, 27,143 twitter messages were analyzed from 22,333 unique Twitter users. We used the Twitter user’s profile descriptions to classify their social identity with the help of computational methods such as Machine Learning and Natural Language Processing. To study the engagement behavior of the Twitter users, we calculated the tweets sentiment and the frequency of interaction between Twitter users and online brand communities. We found that tweet sentiment and frequency of interaction vary significantly between different social identity groups when mentioning different online brand communities. This result is important for online brand community managers to understand what kind of Twitter users interact with their online brand community and how these users engage with the community. Right now, they might only investigate demographics about the users but do not consider the user’s self-presentation online. Furthermore, we made a theoretical contribution by including a larger dataset, by performing computational methods and by exploring multiple online brand communities from different sectors.