Computing in Social Science, Arts and Humanities

Computing in Social Science, Arts and Humanities

  • Abdulbasit Al-Talabani added an answer:
    What are some good tools for emotion extraction from audio features?
    I'm looking for a good tool to extract audio features like Mel-frequency, energy, etc. from a sound file. As my final aim is to extract the emotion of the speaker in the audio, it would be most preferable if I could have a tool that already does basic emotion extraction. I have come across some tools like:
    OpenEAR -
    YAAFE -
    Which could be useful for this task, but I have found that their user-base is not too much and so the tools themselves do not seem to be too user-friendly. Also, since I have still not started working with them, I wanted to know whether there are any better tools available that do the same task, in a better or easier way.
    Abdulbasit Al-Talabani

    OpenEAR software provid a C++ code which work properly under Unix, it extracts more than 6000 LLDs.

  • Philip Gillingham added an answer:
    (As in academia) How would you evaluate a social computing system?
    When comes the evaluation of a social computing system, definitely one of the primary challenges is the number of participants. One obvious problem is how to evaluate the functionality of it. For instance, if you want to evaluate facebook at its early stage, it will create no meaning. Another example could be, if you ask a user in the very early stage of wikis-- whether she would like to read from wikis, definite reply will be no. An utterly rejection by the users is still the most powerful invention in time--wikis and social networking sites. Now I am interested to know, how would you evaluate a new social computing system?

    An argument could be, facebook or wiki proved itself by time, but as an academia--you can not publish your invention in a good venue without an evaluation within the current review format. What is your opinion?
    [ Example: Arranging conference that only targets the ingenuity ]
    Philip Gillingham

    Dear Nasim

    I think your question is a fascinating one, something that I have pondered myself for some time. A key aspect is how you want to evaluate it. In terms of utility, the main focus would be on whether and how people would use it, that is, how useful they find it. Perhaps all you can do is run an trial with a group of people, ie colleagues, students, ask for volunteers on researchgate etc.

    Anyway, still thinking about it....


  • David Charles Wright-Carr added an answer:
    Eye Tracking Devices and Art?
    Eye Tracking Devices (ETDs), developed in Berlin for studies carried out in the International Space Station from 2004 to 2008, and now commercially available from Chronos Vision (, among other companies, have potential for studying how we perceive art.

    In the last decade researchers have used this technology to try to replicate Russian psychologist Alfred L. Yarbus's classic studies of eye movements and art, published in English in 1967 (Yarbus used relatively crude techniques to measure ocular fixations and saccades):

    Marianne Lipps & Jeff B. Pelz, “Yarbus revisited: task-dependent oculomotor behavior,” in Journal of Vision (Association for Research in Vision and Ophthalmology), vol. 4, no. 8, August 13, 2004, article 15 (, access: January 25, 2014).

    Jonathan D. Nelson, Garrison W. Cottrell, Javier R. Movellan & Martin I. Sereno, “Yarbus lives: a foveated exploration of how task influences saccadic eye movement,” in Journal of Vision (Association for Research in Vision and Ophthalmology), vol. 4, no. 8, August 13, 2004, article 741 (, access: January 25, 2014).

    Does anybody know of other studies using ETDs to study how we look at art?
    David Charles Wright-Carr

    The fourth section of the bibliography I recently translated into English and uploaded to ResearchGate includes some recent sources on eye movements:

    • Source
      [Show abstract] [Hide abstract]
      ABSTRACT: This bibliography was prepared for students enrolled in the graduate seminar "Art in the embodied mind" at the University of Guanajuato, and for those participating in the summer research project with the same title. It includes the following thematic sections: 1. Evolutionary aesthetics and paleoneuroaesthetics 2. Neuroscience and the study of the embodied mind 3. Visual perception 4. Eye movements 5. Face recognition and evaluation 6. The embodied mind, neuroaesthetics, and aesthetic psychology 7. The embodied mind, neuroaesthetics, and art education 8. The embodied mind, neuroaesthetics, and art production
  • Shian-Loong Bernard Lew added an answer:
    What work or thoughts have been documented regarding valid model integration, specifically multi-scale model integration?

    What is the state of the art in integrating computational social science models? I am particularly interested in models of phenomena at varying scale (e.g., individual psychological models integrating with social level behavioral or cultural models). 

    Shian-Loong Bernard Lew

    Dear Alicia,

    You're most welcome.

    All the best,


  • Sofian Audry added an answer:
    Are there any records of media art installations that use reinforcement learning?

    I am working on a research on adaptive systems in art practice and would like to know of any media art installations or other forms of artworks (apart from music) that make use of reinforcement learning. The only examples I have been able to find thus far are works that I have authored or co-authored.

    Sofian Audry

    Merci Stephane, quite an interesting project. What was the RL algo used exactly? Did you publish a paper that describes the approach?

  • Shian-Loong Bernard Lew added an answer:
    How can we appeal to students interested in social computing and computational economics?
    I want to foster interest in my department's graduate program by appealing to students who want to do research in social computing and computational economics. Has anyone had good experiences with modern approaches (social media, for example)? Has it been difficult to find students with sufficiently diverse backgrounds (economics + computer science + math + sociology/anthropology/psychology)?
    Shian-Loong Bernard Lew

    By highlighting the fact that simulations are occurring all around them, more so with the mediated technology we use to disguise and to veil interactions- almost an "avatar-ization" of the world. I really hope this word will be the next buzzword for the sake of our students who know it instinctively but would nonetheless have to contend with the textbook principles in order to gain this insight. The dire need therefore is not for more mature students with all-rounded experience but for more imaginative students.

    To quote Albert Einstein (who had frequent flights of imagination):

    “Imagination is more important than knowledge. For knowledge is limited to all we now know and understand, while imagination embraces the entire world, and all there ever will be to know and understand."

  • Richard Rutherford added an answer:
    Teaching a class on 'digital classics' in the spring. Suggested readings, anyone?
    Students will start at a low level of technical competency
    Richard Rutherford

    Thanks for the thread... Just following as interested party and wondering whether the online resources at ISAW (NYU) might be helpful? If not yet familiar with their offerings, see: Good luck with the new course.

  • Djellel Eddine added an answer:
    How can we determine weight of trust in crowdsourced answers/information?
    The growth of the crowd sourced solutioneering phenomenon shows how people will engage and support knowledge development. However, how much confidence can we have in a crowd sourced answer, where we don't know participants, and also some people may be trying to obstruct answers?
    Djellel Eddine

    By comparing with the other answers, you can establish a trust on certain workers. The following "ZenCrowd" technique requires:

    • Run multiple repetitions for each task, ideally >=3.
    • Have a bit of training data, ~5%.
    • note: It was only applied to Multiple choice questions.

    Gianluca Demartini, Djellel Eddine Difallah, and Philippe Cudré-Mauroux: ZenCrowd: Leveraging Probabilistic Reasoning and Crowdsourcing Techniques for Large-Scale Entity Linking. 21st International World Wide Web Conference (WWW2012), Lyon (France), April 16-20, 2012.

  • Ignacio Nieto added an answer:
    Is there anybody who has done research about empathy and eye tracking system?
    Im working for my master thesis, on the fields of: education, computer vision and empathy with children with disabilities. Im starting to program a an aplication who meassure empathy between two groups, and I'm very interested to measure empathy with some device that can just sense the eye.
    Ignacio Nieto

    Hello Saima I dont know Tobii T120 eye tracker, the one they use for the experiment (van Rijn mail, Barendse, Goozen, Swaab), but it seems, that its all done. Using that technology you can report  a heat map without programming it for example

    In these sense the authors said about the experiemnt

    "Gaze data were processed using Tobii Studio (3.0), using the Tobii I-VT fixation filter. The ‘Dynamic AOI (Area of Interest)’ tool, using freeform shapes, was used to draw AOI's. Dynamic AOIs were grouped into the following categories: facial features (without mouth and eyes), eyes, mouth, body, objects and other (i.e. on the screen, outside other AOI's)."

    Also you can work with the Eye Tribe and test heat map making an account in Eyeproof

    When you referer to: "mathematical computations that eye tracking system", what you will need to finish your study? In my case is a little bit more complex Im finishing I hope a first aproach of my research the next week a theorical one. Then I rebuild a software that can detect bad words written by childs with aphasia / SLI. Finally I will meassure empathy.  But all works and people are welcome!


  • Trevor G Bond added an answer:
    Classical test theory and probabilistic test theory: supplementary or contradictory?
    I imagine the following scenario: You have 12 items that measure 2 sub dimensions of a construct, 6 items each construct.

    Say the construct is happiness, the sub dimensions were eudaimonic and hedonic happiness. You find the 2 sub dimensions in an exploratory factor analysis, just as theory says.

    But the Rasch model does not fit each sub dimension. It fits when you analyze ALL items at once. Can we now combine these insights? E.g. we measured each sub dimension reliably and therefore we can assume that items 1e-6e assess eudaimonia, 1h-6h measure hedonia. These items are then labeled with the respective dimension. In Rasch analysis with all items we would then find that 8.3% (=100%/12) participants were measured well per item. Hedonic item 1h has the largest logit, eudaimonic item 1e the second largest, hedonic 2h the third largest, eudaimonic 2e the fourth etc.
    Could we now argue that in the case of happiness the item 1h assesses the most happy persons and this happiness is of hedonic nature?

    In case I messed it up or anything is not clear, please ask.
    Trevor G Bond

    But MIRT is more useful at the estimation of groups, not individual persons

  • Peter T Breuer added an answer:


  • Yaakov HaCohen-Kerner added an answer:
    Can anyone help with natural language processing on screenplays?
    Is anyone aware of any studies applying NLP techniques to screenplay text? I'm aware of some network analytics work, but more interested in studies that apply text analytics techniques.
    Yaakov HaCohen-Kerner
    Dear Gerard,

    Some additional relevant papers might be the following:

    Jhala, A. (2008). Exploiting Structure and Conventions of Movie Scripts for Information Retrieval and Text Mining. In Interactive Storytelling (pp. 210-213). Springer Berlin Heidelberg.‏
    Walker, M. A., Lin, G. I., & Sawyer, J. (2012). An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style. In LREC (pp. 1373-1378).‏
    Kundu, A., Das, D., & Bandyopadhyay, S. (2012, December). Speaker identification from film dialogues. In Intelligent Human Computer Interaction (IHCI), 2012 4th International Conference on (pp. 1-4). IEEE.‏
    Kundu, A. (2013). Identification of Speakers and Scenes from Movie Dialogue(Doctoral dissertation, Department of Computer Science and Engineering, Jadavpur University, India).‏
    Agarwal, A., Balasubramanian, S., Zheng, J., & Dash, S. (2014). Parsing Screenplays for Extracting Social Networks from Movies. EACL 2014, 50-58.‏

    Best regards,
  • Brian Prasad added an answer:
    What is the best qualitative method to understand how to shape knowledge management strategies in a public university?
    Knowledge management
    Brian Prasad
    I am not very knowledgeable on shaping knowledge management strategies in a public university? Since I have worked more number of years in Industries than university.
    I also believe industries are more up in the use of KM strategies than universities are.

    You may find this paper interesting to that effect.

    Total value management — a knowledge management concept for integrating TQM into concurrent product and process development

    Let me know if you find it applicable? Thanks!!
    • Source
      [Show abstract] [Hide abstract]
      ABSTRACT: Most industrial implementations of total quality management (TQM) are based on dimensions, which are ‘quality-oriented’, goals are ‘quality-focused’ or efforts are ‘quality-driven’. Today manufacturing sectors are much more fiercely competitive and global than before. Consumers are more demanding, competition is more contentious and ruthless, and technology is advancing (and changing) rapidly. The quality-based philosophy inherent in a TQM implementation does not exploit the concurrencies present in today's complex product design, development and delivery (PD3) environment. The competitors are always finding better and faster ways of designing and developing products. With the TQM process alone, it is difficult to accomplish all aspects of Total Value Management (TVM) such as X-ability, cost, leanness, responsiveness, agility, tools and technology, and organization issues. A new concurrent Knowledge Management process for Total Value Management is proposed here, which accounts for concurrency — paralleling of value characteristics — along with an integrated methodology for their systematic deployment. Copyright © 2001 John Wiley & Sons, Ltd.
      Knowledge and Process Management 04/2001; 8(2):105 - 122. DOI:10.1002/kpm.112
  • Tahir Sousa added an answer:
    Are there new ways of identification of clauses in sentences?
    What are the best ways to identify clauses in a sentence? I would like to not only extract clauses from a sentence but also identify the type of clause it is. i.e. dependent or independent clause.

    A clause is grammatically defined as the part of the sentence having a subject and predicate. For example consider the sentence:
    "In fact, the last time he tried to lose weight, he ended up actually gaining weight."

    "He tried to lose weight" is a dependent clause while,
    "He ended up actually gaining weight" is an independent clause.

    I have come across some results from CONLL but these are pretty old (2001), so I was wondering whether anyone has an idea to some better work done on this subject.
    Tahir Sousa
    Thanks for all the suggestions everyone! I'm going to take a couple of days to go through all the links and material you have suggested. I'm sure I'll be able to find a nice way to solve the problem with this help. Thanks!
  • Daniel Graziotin added an answer:
    Is there a standard format for technical reports?
    I am writing a technical report describing a piece of software I created for psychological research so that others who use my software can cite it. Is there a standardized format for such a report? Where would you recommend "publishing" it?
    Daniel Graziotin
    Great! Good luck with the peer review process.
  • Gerard Lynch added an answer:
    Does anybody know of any freely available annotated resources containing multiple same language translations of the same source text
    To perform automated analysis of parallel translations of the same works.
    Gerard Lynch
    I found some work which is headed in the direction that I'm interested in, creating parallel data sources of translations and source texts
    I'm not sure if these resources are actually concrete or available yet though.

Topic followers (17,262) See all