Mining online community data: The nature of ideas in online communities

Christensen, Kasper; Liland, Kristian Hovde; Kvaal, Knut; Risvik, Einar; Biancolillo, Alessandra; Scholderer, Joachim; Nørskov, Sladjana; Næs, Tormod

doi:10.1016/j.foodqual.2017.06.001

Cited by 26 publications

(12 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning system we used for extracting the 200 texts is described in detail in Christensen, Nørskov, et al (2017) and Christensen, Liland, et al (2017). Although the technical properties of the system are not the central focus of the present paper, we will give a brief description of the system and how it was employed in our study.…”

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

“…Based on the training set, validation set and hold-out, the automatic idea detection system was trained and tested. The system is based on a linear support vector machine classifier (for details, see Christensen, Liland, et al, 2017). Key performance statistics are reported in Table 1. Of the remaining 7,582 texts (10,582 -3,000 = 7,582) that had not been involved in the training, validation and testing of the system, 200 texts were extracted for the present study by using the linear support vector machine classifier: 100 which the classifier had labelled as idea texts and 100 which the classifier had labelled as non-idea texts.…”

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

“…In this community, people from all over the world discuss brewing-related issues. At the time the texts were extracted, the community contained altogether 10,582 posts, 3,000 of which were selected at random and extracted for the development of the training of the system (detailed results based on these 3,000 texts have been reported in Christensen, Liland, et al, 2017).Those that contained ideas were identified via crowdsourcing, using the CrowdFlower platform (a service similar to Amazon's Mechanical Turk). Five raters were assigned to each text and instructed to label the text as an idea text if it contained at least one idea.…”

mentioning

confidence: 99%

See 3 more Smart Citations

How good are ideas identified by an automatic idea detection system?

et al. 2018

Self Cite

View full text Add to dashboard Cite

Online communities can be an attractive source of ideas for product and process innovations.However, innovative user-contributed ideas may be few. From a perspective of harnessing "big data" for inbound open innovation, the detection of good ideas in online communities is a problem of detecting rare events. Recent advances in text analytics and machine learning have made it possible to screen vast amounts of online information and automatically detect user-contributed ideas. However, it is still uncertain whether the ideas identified by such systems will also be regarded as sufficiently novel, feasible and valuable by firms who might decide to develop them further. A validation study is reported in which 200 posts from an online home brewing community were extracted by an automatic idea detection system. Two professionals from a brewing company evaluated the posts in terms of idea content, idea novelty, idea feasibility and idea value.The results suggest that the automatic idea detection system is sufficiently valid to be deployed for the harvesting and initial screening of ideas, and that the profile of the identified ideas (in terms of novelty, feasibility and value) follows the same pattern identified in studies of user ideation in general. | INTRODUCTIONBig data has been predicted to revolutionize innovation and how firms will create value for themselves, their customers and society (see, e.g., McAfee & Brynjolfsson, 2012). Artificial intelligence systems that leverage big data allow more and more tasks to be solved in an automatic manner. Whilst in the past these were predominantly tasks of a mundane and repetitive nature, advances in text analytics and machine learning have also made it possible to solve more complex problems (Christensen, Nørskov, Frederiksen, & Scholderer, 2017).A problem that continues to occupy scholars and practitioners of new product development is how to obtain and select ideas for new products (e.g., di Gangi, Wasko, & Hooker, 2010;Frederiksen & Knudsen, 2017;van den Ende, Frederiksen, & Prencipe, 2015). In the context of inbound open innovation, Ooms, Bell, and Kok (2015), for example, argue that firms can enhance their receptivity-i.e., their capacity to absorb more diverse external knowledge from more varied sources-by engaging with social media. Whilst this can in theory expand a firm's boundaries for information absorption, the extent of engagement with social media is still constrained by available staff time. Such constraints can to some degree be overcome if companies develop or adopt systems that automate parts of the absorption process.The aim of the research presented here is to show how the performance of automated systems in areas such as inbound open innovation can be evaluated. On one hand, the study should be seen as a feasibility study of whether automated detection of ideas for product and process innovations is actually possible. On the other hand, it should also be regarded as a validation study that probes the "veracity"and "value" aspects of big data (Gandomi ...

show abstract

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

Section: Machine Learning For Idea Detectionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

How good are ideas identified by an automatic idea detection system?

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…This knowledge is not capitalized or structured and its access and reusability by a learner is difficult. If a member wants to benefit from the ideas and the knowledge generated by the online community, the only existing solution is to read everything written and to filter the relevant information manually [7]. In order to facilitate its access and reusability by learners and members interested in that field, this paper propose a framework of knowledge management and reuse in the virtual learning community.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Management and Reuse in Virtual Learning Communities

Sekkal

Amrous

Bennani

2019

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

One of the main sources of knowledge in the web is the social networks and especially online communitie because they contain human experiences which are considered as a rich source of information. This knowledge is in the most cases unstructured and is in the form of discussions organized generally by topics. The aim of this paper is to propose a process of knowledge extraction and Management in Online or Virtual Communities. With the widespread of communities in social media due to the services provided by those technologies, many of those communities are in the form of Learning communities created by expert to share knowledge about a topic of their interest. The knowledge shared by members in the online communities is unfortunately not structured and not capitalized. Many members try to access and learn from the shared knowledge in the community but cannot benefit from it due to its unstructured form. If that knowledge could be represented and stored in order to be reused, it would facilitate the knowledge acquisition by members. For this purpose, the present paper try to analyze the studies that treat the question of extracting and managing knowledge in Online Learning Communities based on several criteria exposed all along this paper. Then we propose a framework for managing knowledge in Virtual Learning communities inspired from the different previous frameworks presented in the analyzed studies, and try to propose and approach to overpass the different challenges present in the actual knowledge Management processes of Virtual Communities.

show abstract

Coordination of Marketing Activity in Online Communities

Peleshchyshyn

Klynina

2019

Advances in Intelligent Systems and Computing IV

View full text Add to dashboard Cite

Mining online community data: The nature of ideas in online communities

Cited by 26 publications

References 51 publications

How good are ideas identified by an automatic idea detection system?

How good are ideas identified by an automatic idea detection system?

Knowledge Management and Reuse in Virtual Learning Communities

Coordination of Marketing Activity in Online Communities

Contact Info

Product

Resources

About