De gustibus disputandum (forecasting opinions by knowledge networks)

Bagnoli, Franco; Berrones, Arturo; Franci, Fabio

doi:10.1016/j.physa.2003.09.065

Cited by 14 publications

(20 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, tastes are in general hidden or difficult to be obtained. If one has at his disposition a sufficient amount of data, it can be shown [6] that the correlation between expressed opinions approximates the real overlap among tastes. This would in principle allow the perfect reconstruction of missing opinions and detection of outliers.…”

Section: Knowledge Networkmentioning

confidence: 99%

Noise and non-linearities in high-throughput data

et al. 2009

Self Cite

View full text Add to dashboard Cite

High throughput data analysis are becoming common in biology, communications, economics and sociology. This vast amount of data are usually represented in form of matrices and can be considered as knowledge networks. Spectralbased approaches have been proved useful in extracting hidden information within such networks and to estimate missing data, but these methods are based essentially on linear assumptions. The physical models of matching, when available, often suggest nonlinear mechanisms, that may sometimes be identified as noise. The use of nonlinear models in data analysis, however, may require the introduction of many parameters, that lowers the statistical weight of the model. According with the quality of data, a simpler linear analysis may be more convenient than more complex approaches.In this paper, we show how a simple nonparametric Bayesian model may be used to explore the role of nonlinearities and noise in synthetic and experimental datasets.

show abstract

Section: Knowledge Networkmentioning

confidence: 99%

Noise and non-linearities in high-throughput data

et al. 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, the vectors may characterize proteins and substrates, or could also represent products in a certain market and agents with different opinions on those products. The overlaps measure the degree of match between a given protein -substrate pair or between a given agent and a product [4]. These overlaps could be infered directly from proteinsubstrate interaction experiments or by market studies.…”

Section: Knowledge Networkmentioning

confidence: 99%

“…For the case in which L is known, Maslov and Zhang [3] have shown the existence of thresholds for the fraction p of known overlaps, above which is possible to reconstruct at different extents the missing information. Bagnoli, Berrones and Franci [4], have generalized the study of Maslov and Zhang to the case in which the dimensionality L is unknown. The present work mainly relies on this last approach, so a brief summary of the results of Bagnoli, Berrones and Franci is now presented.…”

Section: Knowledge Networkmentioning

confidence: 99%

See 1 more Smart Citation

Filtering by Sparsely Connected Networks Under the Presence of Strong Additive Noise

Berrones

2006

2006 Seventh Mexican International Conference on Computer Science

Self Cite

View full text Add to dashboard Cite

A new approach to the problem of noise reduction in signals composed by superpositions of basis functions is proposed. The method is based on interpreting the components of signal models as nodes in a sparsely connected network of overlaps (scalar products). Every point in the data sample expresses an overlap. Networks of this kind, in which nodes carry information by means of vectors, define a knowledge network, a recently introduced concept in the field of statistical physics. Previous results on the statisticalproperties of knowledge networks are generalized to noise reduction and its shown that is possible to extract important hidden quantities. In particular, an algorithm capable to give estimates of the unkown number of degrees of freedom in signal models is constructed and tested.

show abstract

“…Users are modeled as simple perceptrons [16], i.e., they are characterized by a certain number of internal factors, which determine the opinion over a given message by the match between them and the characteristics of the message itself [17].…”

Section: Introductionmentioning

confidence: 99%

Community Formation as a Byproduct of a Recommendation System: A Simulation Model for Bubble Formation in Social Media

et al. 2021

Self Cite

View full text Add to dashboard Cite

We investigate the problem of the formation of communities of users that selectively exchange messages among them in a simulated environment. This closed community can be seen as the prototype of the bubble effect, i.e., the isolation of individuals from other communities. We develop a computational model of a society, where each individual is represented as a simple neural network (a perceptron), under the influence of a recommendation system that honestly forward messages (posts) to other individuals that in the past appreciated previous messages from the sender, i.e., that showed a certain degree of affinity. This dynamical affinity database determines the interaction network. We start from a set of individuals with random preferences (factors), so that at the beginning, there is no community structure at all. We show that the simple effect of the recommendation system is not sufficient to induce the isolation of communities, even when the database of user–user affinity is based on a small sample of initial messages, subject to small-sampling fluctuations. On the contrary, when the simulated individuals evolve their internal factors accordingly with the received messages, communities can emerge. This emergence is stronger the slower the evolution of individuals, while immediate convergence favors to the breakdown of the system in smaller communities. In any case, the final communities are strongly dependent on the sequence of messages, since one can get different final communities starting from the same initial distribution of users’ factors, changing only the order of users emitting messages. In other words, the main outcome of our investigation is that the bubble formation depends on users’ evolution and is strongly dependent on early interactions.

show abstract

De gustibus disputandum (forecasting opinions by knowledge networks)

Abstract: We propose a simple method to predict individuals' expectations about products using a knowledge network. As a complementary result, we show that the method is able, under certain conditions, to extract hidden information at neural level from a customers' choices database.

Cited by 14 publications

References 2 publications

Noise and non-linearities in high-throughput data

Noise and non-linearities in high-throughput data

Filtering by Sparsely Connected Networks Under the Presence of Strong Additive Noise

Community Formation as a Byproduct of a Recommendation System: A Simulation Model for Bubble Formation in Social Media

Contact Info

Product

Resources

About