Dr. Aleksandr Farseev is the Associate Professor @ ITMO University, entrepreneur and the founder of SoMin.AI, the Social Media Marketing platform driven by AI. Supervisors: Tat-Seng Chua
Human personality traits are key drivers behind our decision making, influencing our lives on a d... more Human personality traits are key drivers behind our decision making, influencing our lives on a daily basis. Inference of personality traits, such as the Myers-Briggs personality type, as well as an understanding of dependencies between personality traits and user behavior on various social media platforms, is of crucial importance to modern research and industry applications such as recommender systems. The emergence of diverse and cross-purpose social media avenues makes it possible to perform user personality profiling automatically and efficiently based on data represented across multiple data modalities. However, research efforts on personality profiling from multi-source multi-modal social media data are relatively sparse; the impact of different social network data on profiling performance and of personality traits on applications such as recommender systems is yet to be evaluated. Furthermore, large-scale datasets are also lacking in the research community. To fill these gap...
Proceedings of the AAAI Conference on Artificial Intelligence
Wellness is a widely popular concept that is commonly applied to fitness and self-help products o... more Wellness is a widely popular concept that is commonly applied to fitness and self-help products or services. Inference of personal wellness-related attributes, such as body mass index or diseases tendency, as well as understanding of global dependencies between wellness attributes and users' behavior is of crucial importance to various applications in personal and public wellness domains. Meanwhile, the emergence of social media platforms and wearable sensors makes it feasible to perform wellness profiling for users from multiple perspectives. However, research efforts on wellness profiling and integration of social media and sensor data are relatively sparse, and this study represents one of the first attempts in this direction. Specifically, to infer personal wellness attributes, we proposed multi-source individual user profile learning framework named "TweetFit". "TweetFit" can handle data incompleteness and perform wellness attributes inference from senso...
Proceedings of the AAAI Conference on Artificial Intelligence
The exponential growth of online social networks has inspired us to tackle the problem of individ... more The exponential growth of online social networks has inspired us to tackle the problem of individual user attributes inference from the Big Data perspective. It is well known that various social media networks exhibit different aspects of user interactions, and thus represent users from diverse points of view. In this preliminary study, we make the first step towards solving the significant problem of personality profiling from multiple social networks. Specifically, we tackle the task of relationship prediction, which is closely related to our desired problem. Experimental results show that the incorporation of multi-source data helps to achieve better prediction performance as compared to single-source baselines.
Nowadays, social networks play a crucial role in human everyday life and no longer purely associa... more Nowadays, social networks play a crucial role in human everyday life and no longer purely associated with spare time spending. In fact, instant communication with friends and colleagues has become an essential component of our daily interaction giving a raise of multiple new social network types emergence. By participating in such networks, individuals generate a multitude of data points that describe their activities from different perspectives and, for example, can be further used for applications such as personalized recommendation or user profiling. However, the impact of the different social media networks on machine learning model performance has not been studied comprehensively yet. Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study. Specifically, in this work, we will study the performance of different machine learning models when be...
BackgroundThe rapid spread of the Coronavirus 2019 disease (COVID-19) had drastically impacted li... more BackgroundThe rapid spread of the Coronavirus 2019 disease (COVID-19) had drastically impacted life all over the world. While some economies are actively recovering from this pestilence, others are experiencing fast and consistent disease spread, compelling governments to impose social distancing measures that have put a halt on routines, especially in densely populated areas.ObjectiveAiming at bringing more light on key economic and population health factors affecting the disease spread, this initial study utilizes a quantitative statistical analysis based on the most recent publicly available COVID-19 datasets.MethodsWe have applied Pearson Correlation Analysis and Clustering Analysis (X-Means Clustering) techniques on the data obtained by combining multiple datasets related to country economics, medical system & health, and COVID-19 - related statistics. The resulting dataset consisted of COVID-19 Case and Mortality Rates, Economic Statistics, and Population Public Health Statist...
ACM Transactions on Intelligent Systems and Technology, 2017
Learning user attributes from mobile social media is a fundamental basis for many applications, s... more Learning user attributes from mobile social media is a fundamental basis for many applications, such as personalized and targeting services. A large and growing body of literature has investigated the user attributes learning problem. However, far too little attention has been paid to jointly consider the dual heterogeneities of user attributes learning by harvesting multiple social media sources. In particular, user attributes are complementarily and comprehensively characterized by multiple social media sources, including footprints from Foursqare, daily updates from Twitter, professional careers from Linkedin, and photo posts from Instagram. On the other hand, attributes are inter-correlated in a complex way rather than independent to each other, and highly related attributes may share similar feature sets. Towards this end, we proposed a unified model to jointly regularize the source consistency and graph-constrained relatedness among tasks. As a byproduct, it is able to learn t...
Wellness is a widely popular concept that is commonly applied to fitness and self-help products o... more Wellness is a widely popular concept that is commonly applied to fitness and self-help products or services. Inference of personal wellness--related attributes, such as body mass index (BMI) category or disease tendency, as well as understanding of global dependencies between wellness attributes and users’ behavior, is of crucial importance to various applications in personal and public wellness domains. At the same time, the emergence of social media platforms and wearable sensors makes it feasible to perform wellness profiling for users from multiple perspectives. However, research efforts on wellness profiling and integration of social media and sensor data are relatively sparse. This study represents one of the first attempts in this direction. Specifically, we infer personal wellness attributes by utilizing our proposed multisource multitask wellness profile learning framework—WellMTL—which can handle data incompleteness and perform wellness attributes inference from sensor and...
Human personality traits are key drivers behind our decision making, influencing our lives on a d... more Human personality traits are key drivers behind our decision making, influencing our lives on a daily basis. Inference of personality traits, such as the Myers-Briggs personality type, as well as an understanding of dependencies between personality traits and user behavior on various social media platforms, is of crucial importance to modern research and industry applications such as recommender systems. The emergence of diverse and cross-purpose social media avenues makes it possible to perform user personality profiling automatically and efficiently based on data represented across multiple data modalities. However, research efforts on personality profiling from multi-source multi-modal social media data are relatively sparse; the impact of different social network data on profiling performance and of personality traits on applications such as recommender systems is yet to be evaluated. Furthermore, large-scale datasets are also lacking in the research community. To fill these gap...
Proceedings of the AAAI Conference on Artificial Intelligence
Wellness is a widely popular concept that is commonly applied to fitness and self-help products o... more Wellness is a widely popular concept that is commonly applied to fitness and self-help products or services. Inference of personal wellness-related attributes, such as body mass index or diseases tendency, as well as understanding of global dependencies between wellness attributes and users' behavior is of crucial importance to various applications in personal and public wellness domains. Meanwhile, the emergence of social media platforms and wearable sensors makes it feasible to perform wellness profiling for users from multiple perspectives. However, research efforts on wellness profiling and integration of social media and sensor data are relatively sparse, and this study represents one of the first attempts in this direction. Specifically, to infer personal wellness attributes, we proposed multi-source individual user profile learning framework named "TweetFit". "TweetFit" can handle data incompleteness and perform wellness attributes inference from senso...
Proceedings of the AAAI Conference on Artificial Intelligence
The exponential growth of online social networks has inspired us to tackle the problem of individ... more The exponential growth of online social networks has inspired us to tackle the problem of individual user attributes inference from the Big Data perspective. It is well known that various social media networks exhibit different aspects of user interactions, and thus represent users from diverse points of view. In this preliminary study, we make the first step towards solving the significant problem of personality profiling from multiple social networks. Specifically, we tackle the task of relationship prediction, which is closely related to our desired problem. Experimental results show that the incorporation of multi-source data helps to achieve better prediction performance as compared to single-source baselines.
Nowadays, social networks play a crucial role in human everyday life and no longer purely associa... more Nowadays, social networks play a crucial role in human everyday life and no longer purely associated with spare time spending. In fact, instant communication with friends and colleagues has become an essential component of our daily interaction giving a raise of multiple new social network types emergence. By participating in such networks, individuals generate a multitude of data points that describe their activities from different perspectives and, for example, can be further used for applications such as personalized recommendation or user profiling. However, the impact of the different social media networks on machine learning model performance has not been studied comprehensively yet. Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study. Specifically, in this work, we will study the performance of different machine learning models when be...
BackgroundThe rapid spread of the Coronavirus 2019 disease (COVID-19) had drastically impacted li... more BackgroundThe rapid spread of the Coronavirus 2019 disease (COVID-19) had drastically impacted life all over the world. While some economies are actively recovering from this pestilence, others are experiencing fast and consistent disease spread, compelling governments to impose social distancing measures that have put a halt on routines, especially in densely populated areas.ObjectiveAiming at bringing more light on key economic and population health factors affecting the disease spread, this initial study utilizes a quantitative statistical analysis based on the most recent publicly available COVID-19 datasets.MethodsWe have applied Pearson Correlation Analysis and Clustering Analysis (X-Means Clustering) techniques on the data obtained by combining multiple datasets related to country economics, medical system & health, and COVID-19 - related statistics. The resulting dataset consisted of COVID-19 Case and Mortality Rates, Economic Statistics, and Population Public Health Statist...
ACM Transactions on Intelligent Systems and Technology, 2017
Learning user attributes from mobile social media is a fundamental basis for many applications, s... more Learning user attributes from mobile social media is a fundamental basis for many applications, such as personalized and targeting services. A large and growing body of literature has investigated the user attributes learning problem. However, far too little attention has been paid to jointly consider the dual heterogeneities of user attributes learning by harvesting multiple social media sources. In particular, user attributes are complementarily and comprehensively characterized by multiple social media sources, including footprints from Foursqare, daily updates from Twitter, professional careers from Linkedin, and photo posts from Instagram. On the other hand, attributes are inter-correlated in a complex way rather than independent to each other, and highly related attributes may share similar feature sets. Towards this end, we proposed a unified model to jointly regularize the source consistency and graph-constrained relatedness among tasks. As a byproduct, it is able to learn t...
Wellness is a widely popular concept that is commonly applied to fitness and self-help products o... more Wellness is a widely popular concept that is commonly applied to fitness and self-help products or services. Inference of personal wellness--related attributes, such as body mass index (BMI) category or disease tendency, as well as understanding of global dependencies between wellness attributes and users’ behavior, is of crucial importance to various applications in personal and public wellness domains. At the same time, the emergence of social media platforms and wearable sensors makes it feasible to perform wellness profiling for users from multiple perspectives. However, research efforts on wellness profiling and integration of social media and sensor data are relatively sparse. This study represents one of the first attempts in this direction. Specifically, we infer personal wellness attributes by utilizing our proposed multisource multitask wellness profile learning framework—WellMTL—which can handle data incompleteness and perform wellness attributes inference from sensor and...
Cross-Domain Recommendation via Clustering on Multi-Layer Graphs, 2017
Venue category recommendation is an essential application for
the tourism and advertisement indu... more Venue category recommendation is an essential application for
the tourism and advertisement industries, wherein it may suggest
attractive localities within close proximity to users’ current
location. Considering that many adults use more than three social
networks simultaneously, it is reasonable to leverage on this
rapidly growing multi-source social media data to boost venue recommendation
performance. Another approach to achieve higher
recommendation results is to utilize group knowledge, which is
able to diversify recommendation output. Taking into account these
two aspects, we introduce a novel cross-network collaborative recommendation
framework C3R, which utilizes both individual and
group knowledge, while being trained on data from multiple social
media sources. Group knowledge is derived based on new crosssource
user community detection approach, which utilizes both
inter-source relationship and the ability of sources to complement
each other. To fully utilize multi-source multi-view data, we process
user-generated content by employing state-of-the-art text, image,
and location processing techniques. Our experimental results
demonstrate the superiority of our multi-source framework over
state-of-the-art baselines and different data source combinations.
In addition, we suggest a new approach for automatic construction
of inter-network relationship graph based on the data, which
eliminates the necessity of having pre-defined domain knowledge.
The module introduces the background and present states of social networks and their analysis in ... more The module introduces the background and present states of social networks and their analysis in terms of contents, users, social relations and applications. The social network to be covered include microblogs sites like Twitter, social communication sites like Facebook, location sharing sites like 4Square, and photo sharing sites like Instagram and Flicker. At the end of this tutorial, participants are expected to have initial understanding of the background, design, analysis and implementation of social media analysis systems.
The MBGuide project was started in responce to one of the most important modern challenges: how n... more The MBGuide project was started in responce to one of the most important modern challenges: how not to be lost in the ocean of informations and elaborate technologies, which stay around us everywhere, including journeys? The MBGuide project mission is to provide the tourists and residents with important and relevant information about the sorrounding environment. MBGuide can voice the informations if reading from the screen is inappropriate.
MBGuide is based upon many modern technologies. Utilizing geoinformation server-side API from OpenStreetMap and a client-side speech engine, the application quickly and without extra traffic will provide the smartphone owner with data filtered according to his preferences.
User profile learning, such as mobility and demographic
profile learning, is of great importance... more User profile learning, such as mobility and demographic
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.
The drastic change in the Web was witnessed throughout the past decade, which saw an exponential ... more The drastic change in the Web was witnessed throughout the past decade, which saw an exponential growth in social networking services. The reason of such growth is that social media users concurrently produce and consume data. In this context, millions of users, who follow the different lifestyle and belong to different demographic groups, regularly contribute multi-modal data on various online social networks, such as Twitter, Facebook, Foursquare, Instagram, and Endomondo. Traditionally, social media users are encouraged to complete their profiles by explicitly providing their personal attributes such as age, gender, interest, etc. (individual user profile). Additionally, users are likely to join interest-based groups that are devoted to various topics (group user profile). Such information is essential for different applications, but unfortunately, it is often not available publicly. This gives rise of automatic user profiling, which aims at automatic inferencing of users' unobservable information based on observable information such as individual's behavior or utterances.
This tutorial focused on investigating user profiling across multiple social networks in various application domains. Considering that user profiling can be performed on individual and group levels, this thesis proposes two multi-source learning schemes: multi-source learning scheme for individual user profiling and multi-source community detection scheme for group user profiling. We practically applied the proposed approaches in three user profiling scenarios: demographic profiling, personality profiling, physical wellness profiling, and venue category recommendation.
The thesis focused on investigating user profiling across multiple social networks in Wellness an... more The thesis focused on investigating user profiling across multiple social networks in Wellness and Urban Mobility domains. Considering that user profiling can be performed at individual and group levels, this thesis proposes two multi-source learning schemes: multi-source learning scheme for individual user profiling and multi-source community detection scheme for group user profiling. We practically applied the proposed approaches in three user profiling scenarios: demographic profiling, physical wellness profiling, and venue category recommendation.
The experimental results enable us to draw the following three key findings. First, utilization of multiple data sources improves the performance of individual and group user profiling as well as their applications. Second, it is important to take inter-category relatedness into account when dealing with multiple social networks and sensor data simultaneously. Third, in the context of group user profiling, consideration of inter-network relationship is essential.
Uploads
Papers by Aleksandr Farseev
the tourism and advertisement industries, wherein it may suggest
attractive localities within close proximity to users’ current
location. Considering that many adults use more than three social
networks simultaneously, it is reasonable to leverage on this
rapidly growing multi-source social media data to boost venue recommendation
performance. Another approach to achieve higher
recommendation results is to utilize group knowledge, which is
able to diversify recommendation output. Taking into account these
two aspects, we introduce a novel cross-network collaborative recommendation
framework C3R, which utilizes both individual and
group knowledge, while being trained on data from multiple social
media sources. Group knowledge is derived based on new crosssource
user community detection approach, which utilizes both
inter-source relationship and the ability of sources to complement
each other. To fully utilize multi-source multi-view data, we process
user-generated content by employing state-of-the-art text, image,
and location processing techniques. Our experimental results
demonstrate the superiority of our multi-source framework over
state-of-the-art baselines and different data source combinations.
In addition, we suggest a new approach for automatic construction
of inter-network relationship graph based on the data, which
eliminates the necessity of having pre-defined domain knowledge.
MBGuide is based upon many modern technologies. Utilizing geoinformation server-side API from OpenStreetMap and a client-side speech engine, the application quickly and without extra traffic will provide the smartphone owner with data filtered according to his preferences.
MBGuide: showing you your personal road.
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.
This tutorial focused on investigating user profiling across multiple social networks in various application domains. Considering that user profiling can be performed on individual and group levels, this thesis proposes two multi-source learning schemes: multi-source learning scheme for individual user profiling and multi-source community detection scheme for group user profiling. We practically applied the proposed approaches in three user profiling scenarios: demographic profiling, personality profiling, physical wellness profiling, and venue category recommendation.
The experimental results enable us to draw the following three key findings. First, utilization of multiple data sources improves the performance of individual and group user profiling as well as their applications. Second, it is important to take inter-category relatedness into account when dealing with multiple social networks and sensor data simultaneously. Third, in the context of group user profiling, consideration of inter-network relationship is essential.