Large-Scale Analysis of On-line Conversation about Vaccines before COVID-19

Frequent words and co-occurrences used by pro-vaccination and anti-vaccination communities.

In this study, we map the Twitter discourse around vaccinations in English along four years, in order to:

  • discover the volumes and trends of the conversation;
  • compare the discussion on Twitter with newspapers’ content; and
  • classify people as pro- or anti- vaccination and explore how their behavior is different.

Datasets. We collected four years of Twitter data (January 2016 – January 2020) about vaccination, before the advent of the Covid-19 pandemic, using three keywords: ’vaccine’, ’vaccination’, and ’immunization’, obtaining around 6.5 MLN tweets. The collection has been analyzed across multiple dimensions and aspects. General

Analysis. The analysis shows that the number of tweets related to the topic in- creased through the years, peaking in 2019. Among others, we identified the 2019 measles outbreak as one of the main reasons for the growth, given the correlation of the tweets volume with CDC (Centers for Disease Control and Prevention) data on measles cases in the United States in 2019 and with the high number of newspaper articles on the topic, which both significantly increased in 2019. Other demographic, space-time, and content analysis have been performed too.

Subjects. Besides the general data analysis, we considered a number of specific topics often addressed within the vaccine conversation, such as the flu vaccine, hpv, polio, and others. We identified the temporal trends and performed specific analysis related to these subjects, also in connection with the respective media coverage.

News Sources. We analyzed the news sources most cited in the tweets, which include Youtube, NaturalNews (which is generally considered as a biased and fake news website) and Facebook. Overall, among the most cited sources, 32% can be labeled as reliable and 25% as conspiracy/fake news sources. Furthermore 32% of the references point to social networks (including Youtube). This analysis shows how social media and non-reliable sources of information frequently drive vaccine-related conversation on Twitter.

User Stance. We applied stance analysis on the authors of the tweets, to determine the user’s orientation toward a given (pre-chosen) target of interest. Our initial content analysis revealed that a large amount of the content is of satirical or derisive nature, causing a number of classification techniques to perform poorly on the dataset. Given that other studies considered the presence of stance-indicative hashtags as an effective way to discover polarized tweets and users, a rule-based classification was applied, based on a selection of 100+ hashtags that allowed to automatically classify a tweet as pro-vaccination or vaccination-skeptic, obtain- ing a total of 250,000+ classified tweets over the 4 years.

Share of pro- and anti- vaccine discourse in time. Pro-vaccine tweet volumes appear to be larger than anti-vaccine tweets and to increase over time.

The words used by the two groups of users to discuss of vaccine-related topics are profoundly different, as are the sources of information they refer to. Anti-vaccine users cited mostly fake news websites and very few reliable sources, which are instead largely cited by pro-vaccine users. Social media (primarily Youtube) represent a large portion of linked content in both cases.

Additionally, we performed demographics (age, gender, ethnicity) and spatial analysis over the two categories of users with the aim of understanding the features of the two communities. Our analysis also shows to which extent the different states are polarized pro or against vaccination in the U.S. on Twitter.

Stance of US states towards vaccination.

A video presenting our research is available on YouTube:

This work has been presented at the IC2S2 conference.

The cover image  by NIAID is licensed under CC BY 2.0.

Generation of Realistic Navigation Paths for Web Site Testing using RNNs and GANs

Weblogs represent the navigation activity generated by a specific amount of users on a given website. This type of data is fundamental because it contains information on the behaviour of users and how they interface with the company’s product itself (website or application). If a company could have a realistic weblog before the release of its product, it would have a significant advantage because it can use the techniques explained above to see the less navigated web pages or those to put in the foreground.

A large audience of users and typically a long time frame are needed to produce sensible and useful log data, making it an expensive task. 

To address this limit, we propose a method that focuses on the generation of REALISTIC NAVIGATIONAL PATHS, i.e., web logs .

Our approach is extremely relevant because it can at the same time tackle the problem of lack of publicly available data about web navigation logs, and also be adopted in industry for AUTOMATIC GENERATION OF REALISTIC TEST SETTINGS of Web sites yet to be deployed.

The generation has been implemented using deep learning methods for generating more realistic navigation activities, namely

  • Recurrent Neural Network, which are very well suited to temporally evolving data
  • Generative Adversarial Network: neural networks aimed at generating new data, such as images or text, very similar to the original ones and sometimes indistinguishable from them, that have become increasingly popular in recent years.

We run experiments using open data sets of weblogs as training, and we run tests for assessing the performance of the methods. Results in generating new weblog data are quite good, as reported in this summary table, with respect to the two evaluation metrics adopted (BLEU and Human evaluation).

Picture1

Comparison of performance of baseline statistical approach, RNN and GAN for generating realistic web logs. Evaluation is done using human assessments and BLEU metrics

 

Our study is described in detail in the paper published at ICWE 2020 – International Conference on Web Engineering with DOI: 10.1007/978-3-030-50578-3. It’s available online on the Springer Web site. and can be cited as:

Pavanetto S., Brambilla M. (2020) Generation of Realistic Navigation Paths for Web Site Testing Using Recurrent Neural Networks and Generative Adversarial Neural Networks. In: Bielikova M., Mikkonen T., Pautasso C. (eds) Web Engineering. ICWE 2020. Lecture Notes in Computer Science, vol 12128. Springer, Cham

The slides are online too:

Together with a short presentation video:

 

Are open source projects governed by rich clubs?

The network of collaborations in an open source project can reveal relevant emergent properties that influence its prospects of success.

In our recent joint work with the Open University of Catalunya / ICREA, we analyze open source projects to determine whether they exhibit a rich-club behavior, that is a phenomenon where contributors with a high number of collaborations (i.e., strongly connected within the collaboration network) are likely to cooperate with other well-connected individuals.

ownCloud-open-source-accessibilityThe presence or absence of a rich-club has an impact on the sustainability and robustness of the project. In fact, if a member of the rich club leaves the project, it is easier for other members of the rich club to take over. Less collaborations would require more effort from more users.

The work has been presented at OpenSym 2019, the 15th International Symposium on Open Collaboration, in Skövde (Sweden), on August 20-22, 2019.

The full paper is available on the conference Web Site (or locally here), and the slides presenting our results are available on Slideshare:

For this analysis, we build and study a dataset with the 100 most popular projects in GitHub, exploiting connectivity patterns in the graph structure of collaborations that arise from commits, issues and pull requests. Results show that rich-club behavior is present in all the projects, but only few of them have an evident club structure.

For instance, this network of contributors for the Materialize project seems to go against the open source paradigma. The project is “owned” by very  few users:

richclubEstablished in 2014 by a team of 4 developers, at the time of the analysis it featured 3,853 commits and 252 contributors. Nevertheless, the project only has two top contributors (with more than 1,000 commits), which belong to the original team, and no other frequent contributors.

For all the projects, we compute coefficients both for single source graphs and the overall interaction graph, showing that rich-club behavior varies across different layers of software development. We provide possible explanations of our results, as well as implications for further analysis.

Brand Community Analysis using Graph Representation Learning on Social Networks – with a Fashion Case

In a world more and more connected, new and complex interaction patterns can be extracted in the communication between people.

This is extremely valuable for brands that can better understand  the interests of users and the trends on social media to better target  their products. In this paper, we aim to analyze the communities that arise around commercial brands on social networks to understand the meaning of similarity, collaboration, and interaction among users.

We exploit the network that builds around the brands by encoding it into a graph model. We build a social network graph, considering user nodes and friendship relations; then we compare it with a heterogeneous graph model, where also posts and hashtags
are considered as nodes and connected to the different node types; we finally build also a reduced network, generated by inducing direct user-to-user connections through the intermediate nodes (posts and hashtags). These different variants are encoded using graph representation learning, which generates a numerical vector for each node. Machine learning techniques are applied to these vectors to extract valuable insights for each user and for the communities they belong to.

We report on our experiments performed on an emerging fashion brand on Instagram, and we show that our approach is able to discriminate potential customers for the brand, and to highlight meaningful sub-communities composed by users that share the same kind of content on social networks.

The use case is taken from a joint research project with the Fashion in Process group in the Design Department of Politecnico di Milano, within the framework of FAST (Fashion Sensing Technology).

This study has been published by Springer as part of ACM SAC 2019, Cyprus.

Here is the slideset presenting the idea:

The paper can be referenced as:

Marco Brambilla, Mattia Gasparini: Brand Community Analysis On Social Networks Using Graph Representation Learning. ACM Symposium on Applied Computing (SAC) 2019, pp. 2060-2069.

The link to the officially published paper in the ACM Library will be available shortly.

Possible Theses in Data Science

Here is a presentation that summarizes some of the relevant topics currently available for theses within the Data Science Lab under my supervision.

Feel free to get in touch in case you are interested.

Data Cleaning for Knowledge Extraction and Understanding on Social Media

 

Social media platforms let users share their opinions through textual or multimedia content. In many settings, this becomes a valuable source of knowledge that can be exploited for specific business objectives. Brands and companies often ask to monitor social media as sources for understanding the stance, opinion, and sentiment of their customers, audience and potential audience. This is crucial for them because it let them understand the trends and future commercial and marketing opportunities.

However, all this relies on a solid and reliable data collection phase, that grants that all the analyses, extractions and predictions are applied on clean, solid and focused data. Indeed, the typical topic-based collection of social media content performed through keyword-based search typically entails very noisy results.

We recently implemented a simple study aiming at cleaning the data collected from social content, within specific domains or related to given topics of interest.  We propose a basic method for data cleaning and removal of off-topic content based on supervised machine learning techniques, i.e. classification, over data collected from social media platforms based on keywords regarding a specific topic. We define a general method for this and then we validate it through an experiment of data extraction from Twitter, with respect to a set of famous cultural institutions in Italy, including theaters, museums, and other venues.

For this case, we collaborated with domain experts to label the dataset, and then we evaluated and compared the performance of classifiers that are trained with different feature extraction strategies.

The work has been presented at the KDWEB workshop at the ICWE 2018 conference.

A preprint of the paper can be downloaded and cited as reported here:

Emre Calisir, Marco Brambilla. The Problem of Data Cleaning for Knowledge Extraction from Social Media. KDWeb Workshop 2018, co-located with ICWE 2018, Caceres, Spain, June 2018.

The slides used in the workshop are available online here:

 

IEEE Big Data Conference 2017: take home messages from the keynote speakers

I collected here the list of my write-ups of the first three keynote speeches of the conference:

Driving Style and Behavior Analysis based on Trip Segmentation over GPS Information through Unsupervised Learning

Over one billion cars interact with each other on the road every day. Each driver has his own driving style, which could impact safety, fuel economy and road congestion. Knowledge about the driving style of the driver could be used to encourage “better” driving behaviour through immediate feedback while driving, or by scaling auto insurance rates based on the aggressiveness of the driving style.
In this work we report on our study of driving behaviour profiling based on unsupervised data mining methods. The main goal is to detect the different driving behaviours, and thus to cluster drivers with similar behaviour. This paves the way to new business models related to the driving sector, such as Pay-How-You-Drive insurance policies and car rentals. Here is the presentation I gave on this topic:

Driver behavioral characteristics are studied by collecting information from GPS sensors on the cars and by applying three different analysis approaches (DP-means, Hidden Markov Models, and Behavioural Topic Extraction) to the contextual scene detection problems on car trips, in order to detect different behaviour along each trip. Subsequently, drivers are clustered in similar profiles based on that and the results are compared with a human-defined ground-truth on drivers classification.

The proposed framework is tested on a real dataset containing sampled car signals. While the different approaches show relevant differences in trip segment classification, the coherence of the final driver clustering results is surprisingly high.

 


This work has been published at the 4th IEEE Big Data Conference, held in Boston in December 2017. The full paper can be cited as:

M. Brambilla, P. Mascetti and A. Mauri, “Comparison of different driving style analysis approaches based on trip segmentation over GPS information,” 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, 2017, pp. 3784-3791.
doi: 10.1109/BigData.2017.8258379

You can download the full paper PDF from the IEEE Explore Library, at this url:

https://ieeexplore.ieee.org/document/8258379/

If you are interested in further contributions at the conference, here you can find my summaries of the keynote speeches on human-in-the-loop machine learning and on increasing human perception through text mining.

How Fashionable is Digital Data-Driven Fashion?

Within the context of our data science research track, we have been involved a lot in fashion industry problems recently.

We already showcased some studies in fashion, for instance related to the analysis of the Milano Fashion Week events and their social media impact.

Starting this year, we are also involved in a research and innovation project called FaST – Fashion Sensing Technology. FaST is a project meant to design, experiment with, and implement an ICT tool that could monitor and analyze the activity of Italian emerging Fashion brands on social media. FaST aims at providing SMEs in the Fashion industry with the ability to better understand and measure the behaviours and opinions of consumers on social media, through the study of the interactions between brands and their communities, as well as support a brand’s strategic business decisions.

Given the importance of Fashion as an economic and cultural resource for Lombardy Region and Italy as a whole, the project aims at leveraging on the opportunities given by the creation of an hybrid value chain fashion-digital, in order to design a tool that would allow the codification of new organizational models. Furthermore, the project wants to promote process innovation within the fashion industry but with a customer-centric approach, as well as the design of services that could update and innovate both creative processes and the retail channel which, as of today, represents the core to the sustainability and competitiveness of brands and companies on domestic and international markets.

Within the project, we study social presence and digital / communication strategies of brands, and we will look for space for optimization. We are already crunching a lot of data and running large scale analyses on the topic. We will share our exciting results as soon as available!

 

Acknowledgements

FaST – Fashion Sensing Technology is a project supported by Regione Lombardia through the European Regional Development Fund (grant: “Smart Fashion & Design”). The project is being developed by Politecnico di Milano – Design dept. and Electronics, Information and Bioengineering dept. – in collaboration with Wemanage Group, Studio 4SIGMA, and CGNAL.

logo_w_fondo_transparent 2

Myths and Challenges in Knowledge Extraction and Big Data Analysis

For centuries, science (in German “Wissenschaft”) has aimed to create (“schaften”) new knowledge (“Wissen”) from the observation of physical phenomena, their modelling, and empirical validation.

Recently, a new source of knowledge has emerged: not (only) the physical world any more, but the virtual world, namely the Web with its ever-growing stream of data materialized in the form of social network chattering, content produced on demand by crowds of people, messages exchanged among interlinked devices in the Internet of Things. The knowledge we may find there can be dispersed, informal, contradicting, unsubstantiated and ephemeral today, while already tomorrow it may be commonly accepted.

Picture2The challenge is once again to capture and create consolidated knowledge that is new, has not been formalized yet in existing knowledge bases, and is buried inside a big, moving target (the live stream of online data).

The myth is that existing tools (spanning fields like semantic web, machine learning, statistics, NLP, and so on) suffice to the objective. While this may still be far from true, some existing approaches are actually addressing the problem and provide preliminary insights into the possibilities that successful attempts may lead to.

I gave a few keynote speeches on this matter (at ICEIS, KDWEB,…), and I also use this argument as a motivating class in academic courses for letting students understand how crucial is to focus on the problems related to big data modeling and analysis. The talk, reported in the slides below, explores through real industrial use cases, the mixed realistic-utopian domain of data analysis and knowledge extraction and reports on some tools and cases where digital and physical world have brought together for better understanding our society.

The presentation is available on SlideShare and are reported here below: