About Me
My contributions go to the development of AI systems in the field of Fake news/Disinformation …
** Research Interests: **
-
** Machine Learning/Deep Learning:** Classical Algorithms (e.g., SVM, RF) to Deep Neural Network to solve supervised and semi-supervised problems.
-
Applicative Contexts: Natural Language Processing, Behavioral and Social Signal Processing (Emotion, Personality traits) from Speech and Text; Social Media Text Analysis.
Short Bio: Currently working for QCRI, Qatar, as a Scientist. I received my PhD in Computer Science from the University of Trento, under the supervision of Prof. Giuseppe Riccardi, master’s from the same department, and undergrad from BRAC University.
Affliated member: IEEE, AAAI, ACM, ISCA, AAAC
Recent News
- E.M.P.A.T.H.Y. acronym
- ICASSP 2014
- Paper accepted in ICASSP-2014
- Studying emotion and personality traits
Recent Publications
-
Ofli, F., Imran, M., & Alam, F. (2020). Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview. In AI and Robotics in Disaster Studies (pp. 63–81). Springer.
@inbook{ofli2020using, title = {Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview}, author = {Ofli, Ferda and Imran, Muhammad and Alam, Firoj}, booktitle = {AI and Robotics in Disaster Studies}, pages = {63--81}, year = {2020}, publisher = {Springer}, note = {https://link.springer.com/chapter/10.1007/978-981-15-4291-6_5} }
The ever-increasing popularity of social media platforms has transformed the way in which information is shared during disasters and mass emergencies. Information that emanates from social media, especially in the early hours of a disaster when little-to-no information is available from other traditional sources, can be extremely valuable for emergency responders and decision makers to gain situational awareness and plan relief efforts. To capitalize on this potential, extensive research and development activities have been conducted over the last decade to build technologies to support various humanitarian aid tasks. In this paper, we provide an overview of the literature on using artificial intelligence and social media for disaster response and management from three perspectives: datasets, research studies, and systems. Then, we present further discussion on open research problems and future directions in the crisis informatics domain. -
Ofli, F., Imran, M., & Alam, F. (2020). Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview. In AI and Robotics in Disaster Studies (pp. 63–81). Springer.
@inbook{ofli2020usinh, title = {Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview}, author = {Ofli, Ferda and Imran, Muhammad and Alam, Firoj}, booktitle = {AI and Robotics in Disaster Studies}, pages = {63--81}, year = {2020}, publisher = {Springer}, note = {https://www.springerprofessional.de/en/using-artificial-intelligence-and-social-media-for-disaster-resp/18475194} }
The ever-increasing popularity of social media platforms has transformed the way in which information is shared during disasters and mass emergencies. Information that emanates from social media, especially in the early hours of a disaster when little-to-no information is available from other traditional sources, can be extremely valuable for emergency responders and decision makers to gain situational awareness and plan relief efforts. To capitalize on this potential, extensive research and development activities have been conducted over the last decade to build technologies to support various humanitarian aid tasks. In this paper, we provide an overview of the literature on using artificial intelligence and social media for disaster response and management from three perspectives: datasets, research studies, and systems. Then, we present further discussion on open research problems and future directions in the crisis informatics domain. -
Alam, F., Danieli, M., & Riccardi, G. (2019). Automatic Labeling Affective Scenes in Spoken Conversations. In Cognitive Infocommunications, Theory and Applications (pp. 109–130). Springer.
@inbook{alam2019automatic, title = {Automatic Labeling Affective Scenes in Spoken Conversations}, author = {Alam, Firoj and Danieli, Morena and Riccardi, Giuseppe}, booktitle = {Cognitive Infocommunications, Theory and Applications}, pages = {109--130}, year = {2019}, publisher = {Springer}, note = {https://link.springer.com/chapter/10.1007/978-3-319-95996-2_6} }
Research in affective computing has mainly focused on analyzing human emotional states as perceivable within limited contexts such as speech utterances. In our study, we focus on the dynamic transitions of the emotional states that are appearing throughout the conversations and investigate computational models to automatically label emotional states using the proposed affective scene framework. An affective scene includes a complete sequence of emotional states in a conversation from its start to its end. Affective scene instances include different patterns of behavior such as who manifests an emotional state, when it is manifested, and which kinds of changes occur due to the influence of one’s emotion onto another interlocutor. In this paper, we present the design and training of an automatic affective scene segmentation and classification system for spoken conversations. We comparatively evaluate the contributions of different feature types in the acoustic, lexical and psycholinguistic space and their correlations and combination. -
Alam, F., Magnini, B., & Zanoli, R. (2015). Comparing Named Entity Recognition on Transcriptions and Written Texts, Harmonization and Development of Resources and Tools for Italian Natural Language Processing within the PARLI Project. In R. Basili, C. Bosco, R. Delmonte, A. Moschitti, & M. Simi (Eds.), Vol. 589 (Vol. 589). Springer.
@inbook{alam2015comparing, author = {Alam, Firoj and Magnini, Bernardo and Zanoli, Roberto}, editor = {Basili, R. and Bosco, C. and Delmonte, R. and Moschitti, A. and Simi, M.}, journal = {Vol. 589}, publisher = {Springer}, title = {Comparing {Named} {Entity} {Recognition} on {Transcriptions} and {Written} {Texts}, {Harmonization} and {Development} of {Resources} and {Tools} for {Italian} {Natural} {Language} {Processing} within the {PARLI} {Project}}, volume = {589}, year = {2015} }
-
Alam, F., & Zanoli, R. (2013). A Combination of Classifiers for Named Entity Recognition on Transcription. In B. Magnini, F. Cutugno, M. Falcone, & E. Pianta (Eds.), Evaluation of Natural Language and Speech Tools for Italian (pp. 107–115). Springer.
@inbook{alam2013combination, author = {Alam, Firoj and Zanoli, Roberto}, booktitle = {Evaluation of Natural Language and Speech Tools for Italian}, editor = {Magnini, Bernardo and Cutugno, Francesco and Falcone, Mauro and Pianta, Emanuele}, pages = {107--115}, publisher = {Springer}, title = {A Combination of Classifiers for Named Entity Recognition on Transcription}, note = {https://link.springer.com/chapter/10.1007/978-3-642-35828-9_12}, year = {2013} }
This paper presents a Named Entity Recognition (NER) system on broadcast news transcription where two different classifiers are set up in a loop so that the output of one of the classifiers is exploited by the other to refine its decision. The approach we followed is similar to that used in Typhoon, which is a NER system designed for newspaper articles; in that respect, one of the distinguishing features of our approach is the use of Conditional Random Fields in place of Hidden Markov Models. To make the second classifier we extracted sentences from a large unlabelled corpus. Another relevant feature is instead strictly related to transcription annotations. Transcriptions lack orthographic and punctuation information and this typically results in poor performance. As a result, an additional module for case and punctuation restoration has been developed. This paper describes the system and reports its performance which is evaluated by taking part in Evalita 2011 in the task of Named Entity Recognition on Transcribed Broadcast News. In addition, the Evalita 2009 dataset, consisting of newspapers articles, is used to present a comparative analysis by extracting named entities from newspapers and broadcast news.
My interview with Sage
Using Twitter and Applied Artificial Intelligence for Natural Disaster Relief “I think most important is finding the problem that is important to solve for the community”
I think most important is finding the problem that is important to solve for the community
AIDR Image Processing Pipeline
A complete pipeline for crawling image to their classification.
PhD Thesis
The Design of Computational models for Analyzing Personality and Affective Behavioral Signals (particular focus on empathy) from speech and text
-
“Who expresses what emotional state when?”,
-
Conversation summarization with behavoiral descriptions in terms of emotion, topic and sentiment by utilizing NLP and Machine Learning techniques from spoken conversations and social media data. www.sensei-conversation.eu