Conference PaperPDF Available

An Implicit-Semantic Tag Recommendation Mechanism for Socio-Semantic Learning Systems

Authors:

Abstract and Figures

In recent years Social Tagging (ST) has become a popular functionality in social learning environments, not least because tags support the exchange of users’ knowledge representations, a process called social sensemaking. An important design feature of ST-Systems (STS) is the tag recommendation service. Several principles for tag recommendation mechanisms (TRM) have been proposed, which are built upon a technical and statistical perspective on STS and based on aggregated user data on a word level. Up to now, a cognitive perspective also taking into account memory processes has been neglected. In this paper we therefore introduce a TRM that applies a formal theory of human memory to model a user’s prototypical tag configurations. The algorithm underlying the TRM is supposed to recommend psychologically plausible tag combinations and to mediate social sensemaking.
Content may be subject to copyright.
An Implicit-Semantic Tag Recommendation Mechanism
for Socio-Semantic Learning Systems
Paul Seitlinger1, Tobias Ley2, and Dietrich Albert1
1 Knowledge Management Institute, Graz University of Technology, Austria
{paul.seitlinger,dietrich.albert}@tugraz.at
2 Center for Educational Technology, Tallinn University, Estonia
tley@tlu.ee
Abstract. In recent years Social Tagging (ST) has become a popular functionali-
ty in social learning environments, not least because tags support the exchange
of users’ knowledge representations, a process called social sensemaking. An
important design feature of ST-Systems (STS) is the tag recommendation ser-
vice. Several principles for tag recommendation mechanisms (TRM) have been
proposed, which are built upon a technical and statistical perspective on STS
and based on aggregated user data on a word level. Up to now, a cognitive per-
spective also taking into account memory processes has been neglected. In this
paper we therefore introduce a TRM that applies a formal theory of human
memory to model a user’s prototypical tag configurations. The algorithm under-
lying the TRM is supposed to recommend psychologically plausible tag combi-
nations and to mediate social sensemaking.
Keywords: Tagging, Categorization, Cognitive Modelling, MINERVA2, Tag-
Recommendation-Algorithm
1 Introduction
In recent years, Social Tagging (ST) has become a popular functionality in the Web
allowing people to freely associate textual labels (called tags) to resources. Prominent
ST-Systems (STS) are http://del.icio.us (social bookmarking platform) or
http://flickr.com (photo sharing platform), which we regard as socio-semantic learn-
ing environments. Dynamic interactions between representations on an external level
(tags and resources) and semantic memory processes on an internal level (categoriza-
tion) expedite social sensemaking [1], i.e. cooperative categorization and indexing of
Web resources. To mediate these social learning processes we need services that ana-
lyze statistical structures on the word level and are embedded into a cognitive-
psychologically plausible framework.
With respect to its usefulness for educational activities, empirical studies of Kuhn
et al. (e.g. [5]) give evidence that ST supports an important aspect of science educa-
tion in schools and university courses, namely reflecting on the utility of data and
annotating this reflection for later recall. A design recommendation of [5] is that
teachers or lectors deploying ST for social learning processes should provide a sche-
ma for the tagging activity and should categorize tags in a relevant way.
In this paper we introduce the principles of a tag-recommendation mechanism (TRM),
which is motivated by empirical studies [6,7] and built upon MINERVA 2 [3], a for-
mal theory of human memory. This TRM is designed to extract prototypical tag com-
binations (so called gist traces) from a user's tagging behavior and to suggest tags in a
categorized and psychologically meaningful way. The suggestion of gist-traces is
supposed to give a supportive schema during the tagging activity. Beyond that, it is
conceived to identify and recommend users with similar gist traces, thereby mediating
social sensemaking.
The structure of this article is as follows. First, we provide a brief overview of pre-
vious TRMs (section 2.1). Second, we briefly summarize some cognitive-
psychological work on STS to motivate the principles of our TRM and briefly de-
scribe MINERVA2 (section 2.2). Third, we provide simple equations to derive appro-
priate tag recommendations (sections 2.3 and 2.4).
2 An Implicit-Semantic Tag Recommendation Mechanism
2.1 Previous Tag Recommendation Mechanisms
Referring to [2] there are currently four different approaches to design TRMs. One
approach is the analysis of tag quality, e.g. its popularity and semantic distinctiveness
to other tags. A second approach is the computation of tag co-occurrence to gather
similarities between pairs of tags for the recommendation of appropriate tag combina-
tions. The third approach relies on mutual information between words, documents and
tags. One example is collaborative filtering for recommending tags in folksonomies
[4]. For a given user a neighborhood is formed consisting of users with similar tag or
resource collections. Tags frequently occurring within the neighborhood are then
recommended. The fourth approach takes into account the content of a resource and
ranks tags according to their relevance to the resource’s content. [4] applied an
adapted PageRank algorithm, which ranks the importance of vertices (tags, users,
resources) as a function of their edge degrees. The most dominant approach simply
counts the number of tag occurrences and suggests the most popular ones.
All these approaches are based on aggregated user data and to some extent on
the “wisdom of the crowd”. However, they abstract from users’ preferences and ne-
glect their typically verbal categorization behavior. Cognitive-psychological studies
(e.g. [1,6,7]), briefly described in the next sub-section, show that these approaches
would benefit from mechanisms applying formal theories of human semantic
memory. Such an extension would help to realize the suggestion of [5] to provide a
categorical schema for the tagging activity during educational tasks.
2.2 Theoretical and Empirical Background
[1] provided a formal model of human categorization in STS. They put emphasis on
implicit (automatic) categorization processes of a user during a tag-based inference of
a resource’s gist (topic) as well as during gist-based tag-assignments. By means of a
multinomial model of ST [6] and [7] empirically showed that implicit categorization
processes (gist-based reconstructions) are indeed in play during the generation of tags.
More precisely, users retrieve an implicit gist-trace from their semantic memory to
reconstruct the meaning of previously perceived tags. Afterwards, tags are chosen to
index the implicit gist-trace. Here, we introduce an implicit-semantic tag-
recommendation mechanism (isTRM) that mimics the gist-based reconstruction pro-
cess investigated by [6].
As described above, the isTRM is built upon MINERVA2 [3] that formally de-
scribes implicit, reconstructive processes triggered by stimuli (e.g. words or tags). The
general assumption is that a stimulus (e.g. the word “bird”) strongly activates traces
(internal representations) in semantic memory, which share many features with the
stimulus (e.g. sparrow, raven, falcon, etc.); all other traces stay relatively dormant
(e.g. different dog exemplars). All the features common across the activated traces
(e.g. feathers, wings, etc.) constitute the concept that comes into mind. The outcome
of this activation process is a prototype or gist: an abstract representation of all single
traces activated by the stimulus (e.g. a prototypical bird). MINERVA2 provides a
formalization of this reconstructive process. Memory traces as well as stimuli are
formalized as vectors where feature values (-1, 1) encode the existence/nonexistence
of features. Thus, the semantic memory is represented as a matrix (a set of row vec-
tors). A particular algorithm (see 2.4), which multiplies the matrix by a stimulus-
vector, yields a content-vector displaying the prototype.
We draw on the MINERVA2 notations to represent a user’s tag assignments (TAS
for short) in form of vectors, whose feature values encode the assignment/non-
assignment of a tag to a particular resource, and on the MINERVA2 algorithm to
extract the user’s prototypical tag combinations.
2.3 Notation of a User’s Personomy
The basis of the isTRM is the formalization of a user’s semantic traces left in the STS,
which are verbalized in form of her or his tag assignments (TAS). To define a TAS
we refer to [4] and represent an STS as a triple of the finite sets U, T and R, whose
elements are the users, tags and resources, respectively. There exists a ternary relation
Y between the three sets, i.e. Y U × T × R., and the TAS (u, t, r) are the elements of
Y. The collection of all TAS of user ui is called personomy [4]; the collection of all
personomies constitutes the folksonomy.
For m resources and n tags of the whole folksonomy, we notate the personomy of a
user ui in a resource-tag matrix X {-1,1}m×n that can be divided into row vectors: X
],...,[: 1m
xx
with
],...[: 1rnrr xxx
, for r := 1,…,m. We call xrt a tag-feature indi-
cating that a user assigned tag t to the resource r, and xrt {-1,1}. Thus, each row
vector represents a particular TAS of a user ui that we call semantic trace. The middle
part of Fig.1 schematically presents this resource-tag matrix X. For instance, the first
tag-feature of the semantic trace
1
x
indicates that the user assigned the tag “memory”
to the resource r1; the second tag-feature represents the non-assignment of the tag
“Java”.
Fig. 1. Schematic presentation of the isTRM mechanics.
One prerequisite to apply MINERVA2 is to group the semantic traces of a user into
categories. In several social platforms, such as MENDELEY (www.mendeley.com),
SemanticScuttle (www.semanticscuttle.sourceforge.net) or soboleo
(www.soboleo.com), self-created folders or taxonomies complement the tagging func-
tionality. In such environments, each folder or node of the taxonomy can be interpret-
ed as a category cat. In more popular STS, such as Del.icio.us (www.delicious.com),
some additional computational costs have to be invested to identify categories. The
following paragraph provides a suggestion on how to group resources into categories.
Similar to the technique of collaborative filtering, the similarities between pairs of
semantic traces, e.g.
),( 21 xx
, can be computed by the cosine similarity measure (e.g.
[4]). This measure can be applied to all pairs of semantic traces and a subsequent
multidimensional scaling can represent these vectors as points in a multidimensional
space. All pairs of traces whose Euclidean distance d does not exceed a critical
threshold
can be assigned to the same category cati. Each vector
r
x
needs a “label”
indicating its category membership. Therefore, we extend each semantic trace by o
(so called) category-features t = n+1 n+o, representing the category to which re-
source r belongs. For simplicity, in the example of Fig.1 there are only five category-
features (i.e. o=5), which would allow for 25 differentiations. For instance, the seman-
tic trace
1
x
is labeled by the sequence [1,1,1,1,1].
2.4 Extracting the Gist of a User’s Tag-Assignments
After a new resource rnew, has been assigned to a category, e.g. cat1, the isTRM starts
by generating a probe P (circled “1” in Fig. 1). The purpose of P is to activate those
semantic traces in the matrix X, which belong to the same or similar category as the
resource rnew. P is also a vector with tag-features [pt=1 n] and category-features
[pt=n+1 … n+o] and bears the same label (category-features) as the resource rnew
(1,1,1,1,1 in the example of Fig.1); its tag-features are set at 0. A particular
MINERVA2 equation yields the similarity S(
r
x
) between P and a semantic trace
r
x
by
(1)
NR is the number of features for which either pt or xrt is nonzero. Since S(
r
x
) acts
in a similar way as the Pearson correlation coefficient, the value of S(
r
x
) will be
positive and high (approaching +1) for all traces bearing the same or a similar label as
P (
1
x
in the example of Fig.1). The extent to which P activates the trace
r
x
depends
on a non-linear function of S(
r
x
) given by A(
r
x
) = S(
r
x
)3. Raising S(
r
x
) to the
power 3 has proved to increase the activation differences between similar and less
similar traces (see [3]).
To derive tag-recommendations from the matrix a content Vector C with content-
features ct is computed summarizing the activation pattern across the matrix (circled
“3” in Fig.1). The activation of each trace A(
r
x
) is multiplied by each of the trace’s
feature xrt (circled “2” in Fig.1). Then, these products are summed over traces:
.)(
1
m
rrtrt xxAc
(2)
The ct values indicate, “which features [in our case tags] are shared by the strong-
ly activated traces” [3] and therefore, which tags belong to a prototypical tag combi-
nation of a user. In the example of Fig.1 the tags “memory”, “brain” and “recall”
constitute such a prototypical tag combination. Finally, we need a simple rule select-
ing an appropriate subset of tags for the gist-trace, i.e. the final tag recommendations.
If the parameter l specifies the number of tags to be selected, an appropriate subset is
given by gist-trace := {ct ϵ C | rank(ct) ≤ l}.
The isTRM is also conceived to mediate social sensemaking by identifying neigh-
borhoods of users with similar categorization behavior. That could be realized by
combining collaborative filtering with the content vector C. Referring to [4] the k
most similar users to user u can be computed by:
),,(maxarg: {u}\ vu
k
Uv
k
uCCsimN
(3)
where sim(Cu,Cv) is the cosine similarity between two vectors, in our case content
vectors of the users u and v. We assume that the neighborhood of user u based on
content vectors is a valid measure for user recommendations from a semantic memory
perspective.
3 Summary and Conclusion
In this paper we introduced the isTRM, an implicit tag recommendation mechanism
for the suggestion of psychologically plausible tag combinations and the identification
of users with similar categorization behavior. It is based on empirical research on ST,
built upon the memory theory MINERVA2 and treats users’ TAS as verbalized se-
mantic traces. The outcome of the isTRM is a gist-trace representing a tag combina-
tion that is assumed to resonate with the user’s implicit semantic memory and thus, to
give an appropriate categorical schema during the tagging activity, as suggested by
[5]. By incorporating collaborative filtering, the isTRM appears to be a psychological-
ly valid service to mediate social sensemaking within social learning environments.
In the near future, we aim at evaluating the isTRM. We will conduct an empirical
study where different groups of participants will be supported by conventional TRMs
as well as by the isTRM. On the one hand we will measure group differences with
respect to the acceptance ratio, operationalized by the variables recall and precision
(see [4]). On the other hand we will investigate the impact of the isTRM) on social
sensemaking, operationalized by tag-quality (e.g. semantic distinctiveness) and re-
source-quality (e.g. coverage of different categories of the knowledge domain).
4 References
1. Fu, W.-T., Kannampallil, T.G., & Kang, R.: A semantic imitation model of social
tag choices. In: Proceedings of CSE’09, pp. 66-73. ACM-press, New York
(2009).
2. Gupta, M., Li, R., Yin, Z., & Han, J.: Survey on social tagging techniques. In:
17th ACM SIGKDD, pp. 58-72. ACM-press, New York (2010).
3. Hintzman, D.L.: MINERVA 2: a simulation model of human memory. Behav.
Res. Meth. Ins. C. 16, 96-101 (1984).
4. Jäschke, R., Marinho, L., Hotho, A., Schmidt-Thieme, L., & Stumme, G.: Tag
recommendations in social bookmarking systems. AI Commun. 21, 231-247
(2008).
5. Kuhn, A., Cahill, C., Quintana, C., & Schmoll, S.: Using tags to encourage reflec-
tion and annotation on data during nomadic inquiry. In: Proceedings of CHI’11,
pp. 667-670. ACM-press, New York (2011).
6. Seitlinger, P., & Ley, T.: Implicit imitation in social tagging: familiarity and se-
mantic reconstruction. In: Proceedings of CHI’12, pp.1631-1640, ACM-press.
New York (2012).
7. Seitlinger, P., & Ley, T.: Implicit and explicit memory in social tagging: evidence
from a process dissociation procedure. In: Proceedings of ECCE’11, pp. 97-104,
ACM-Press. New York (2011).
... This may not only be true for tag-based navigation , but potentially also for the imitation of tags (W.-T. Fu, Kannampallil, Kang, & He, 2010;Seitlinger, 2012;Seitlinger et al., 2015). ...
... After navigating with tags, people remember more popular concepts compared to less popular concepts Seitlinger, 2012). ...
... The present study showed that implicit presentation of expertise is even more effective than the explicit one. Earlier research (Seitlinger, 2012) showed that tag semantics and popularity determine individual information processing behavior. Likewise, previous studies successfully showed that social tags influence information selection, evaluation, incidental learning Held et al., 2012), and conceptual memory representations Seitlinger, 2012). ...
Thesis
Full-text available
Confirmation bias is the tendency of information searchers to select and evaluate information that supports pre-existing attitudes favourably. The current dissertation investigates whether confirmation bias affects health-related search in online environments, where users share content and social tag clouds are the navigation interface for searchers. I assumed that when individuals search health-related issues, they are motivated to find accurate information (accuracy motivation), in contrast to defending their self-concept (defense motivation). To determine what information is accurate, I expect that searchers attend to internal, individual evaluations (prior knowledge, prior attitudes, and attitude confidence), and external, collective cues (tag popularity and source credibility). Regarding the influence of individual evaluations, in studies 2 and 3, a linear influence of prior attitudes on the selection of blog posts (but not tags), and the evaluation of blog posts was found. In studies 2 and 3, I tested whether the influence of prior attitudes was moderated by confidence. I found that high confidence did affect the selection of blog posts but not tags in both studies, and confidence influenced the evaluation of tag-related blog posts. Regarding the influence of the collective cues, tag popularity was manipulated in studies 1 and 3, where I found a main effect of tag popularity on the selection of tags, blog posts, and evaluation of content, showing that tag size influenced confirmation bias in a moderate to strong way. In the student sample (study 2), I found that high credibility reduced the influence of prior attitudes on the selection of tags and consequently blog posts. However, using a representative sample (study 3), no influence of source credibility was found. With respect to the searchers’ evaluation of content, credibility had no influence in study 2, but in study 3, under high source credibility and low attitude confidence, searchers evaluated content more favourably when content was attitude consistent. In conclusion, the present dissertation shows that confirmation bias and individual evaluations guide information searchers in tag-based navigation, extending the literature which showed behaviour in social tagging environments follows semantic associations. The results are interesting for the construction of content aggregation or social tagging platforms, and practitioners who provide health-related online content. Practitioners and platform providers pay attention to their target audience, as this will either elicit accuracy or defense motivation. So, different strategies can be implemented when the aim is to reduce the influence of confirmation bias on information search behaviour.
... MINERVA2 (Hintzman, 1984), BLL (John R. Anderson, Bothell, et al., 2004)). Both approaches have been suggested for the application in tag recommender systems (Seitlinger, Ley, and Albert, 2013;Kowald, Seitlinger, Trattner, et al., 2014). ...
... Application in Tagging. Seitlinger, Ley, and Albert (2013) have further looked into MINERVA2's schema abstraction approach in order to mimic how humans retrieve words from memory, when confronted with external, contextual stimuli (e.g., topics). More precisely, a computation model for tagging in social learning systems is introduced. ...
... BLL implements the Base Level Learning Equation (John R. Anderson and Schooler, 1991), which models the frequency and recency of past tag use. MINERVA2 (Hintzman, 1984;Seitlinger, Ley, and Albert, 2013), incorporates tag use frequency as well as semantic context. ...
Article
Full-text available
In recent years, various recommendation algorithms have been proposed to support learners in technology-enhanced learning environments. Such algorithms have proven to be quite effective in big-data learning settings (massive open online courses), yet successful applications in other informal and formal learning settings are rare. Common challenges include data sparsity, the lack of sufficiently flexible learner and domain models, and the difficulty of including pedagogical goals into recommendation strategies. Computational models of human cognition and learning are, in principle, well positioned to help meet these challenges, yet the effectiveness of cognitive models in educational recommender systems remains poorly understood to this date. This thesis contributes to this strand of research by investigating i) two cognitive learner models (CbKST and SUSTAIN) for resource recommendations that qualify for sparse user data by following theory-driven top down approaches, and ii) two tag recommendation strategies based on models of human cognition (BLL and MINERVA2) that support the creation of learning content meta-data. The results of four online and offline experiments in different learning contexts indicate that a recommendation approach based on the CbKST, a well-founded structural model of knowledge representation, can improve the users? perceived learning experience in formal learning settings. In informal settings, SUSTAIN, a human category learning model, is shown to succeed in representing dynamic, interest based learning interactions and to improve Collaborative Filtering for resource recommendations. The investigation of the two proposed tag recommender strategies underlined their ability to generate accurate suggestions (BLL) and in collaborative settings, their potential to promote the development of shared vocabulary (MINERVA2). This thesis shows that the application of computational models of human cognition holds promise for the design of recommender mechanisms and, at the same time, for gaining a deeper understanding of interaction dynamics in virtual learning systems.
... MINERVA2 (Hintzman, 1984), BLL (John R. Anderson, Bothell, et al., 2004)). Both approaches have been suggested for the application in tag recommender systems (Seitlinger, Ley, and Albert, 2013;Kowald, Seitlinger, Trattner, et al., 2014). ...
... Application in Tagging. Seitlinger, Ley, and Albert (2013) have further looked into MINERVA2's schema abstraction approach in order to mimic how humans retrieve words from memory, when confronted with external, contextual stimuli (e.g., topics). More precisely, a computation model for tagging in social learning systems is introduced. ...
... BLL implements the Base Level Learning Equation (John R. Anderson and Schooler, 1991), which models the frequency and recency of past tag use. MINERVA2 (Hintzman, 1984;Seitlinger, Ley, and Albert, 2013), incorporates tag use frequency as well as semantic context. ...
... In our previous work [23,21], we have intensively investigated the suitability of two tag recommendation approaches via offline studies [21]: the first called (Bi) is inspired by the Base Level Learning Equation (BLL) [1], which models the frequency and recency of past tag use. The second algorithm, called Minerva [17,34], incorporates tag use frequency as well as semantic context. Both approaches aim to imitate cognitive processes of retrieving words from memory. ...
... The M inerva model aims to mimic a process of human categorization as introduced and described in [34]. It consists of a simple network model with an input, a hidden and an output layer. ...
Conference Paper
Full-text available
In online social learning environments, tagging has demonstrated its potential to facilitate search, to improve recommendations and to foster reflection and learning. Studies have shown that as a prerequisite for learning, shared understanding needs to be established in the group. We hy-pothesise that this can be fostered through tag recommendation strategies that contribute to semantic stabilization. In this study, we investigate the application of two tag rec-ommenders that are inspired by models of human memory: (i) the base-level learning equation BLL and (ii) Minerva. BLL models the frequency and recency of tag use while Min-verva is based on frequency of tag use and semantic context. We test the impact of both tag recommenders on semantic stabilization in an online study with 51 students completing a group-based inquiry learning project in school. We find that displaying tags from other group members contributes significantly to semantic stabilization in the group, as compared to a strategy where tags from the students' individual vocabularies are used. Testing for the accuracy of the different recommenders revealed that algorithms using frequency counts such as BLL performed better when individual tags were recommended. When group tags were recommended, the Minerva algorithm performed better. We conclude that tag recommenders, exposing learners to each other's tag choices by simulating search processes on learn-ers' semantic memory structures, show potential to support semantic stabilization and thus, inquiry-based learning in groups.
... The second influence on confirmation bias occurs when people face cues from socially aggregated information on the web [19][20][21][22][23][24]. Cues indicating socially aggregated information include star ratings, likes, retweet counts, or social tags. ...
Article
Full-text available
Background: In health-related, Web-based information search, people should select information in line with expert (vs nonexpert) information, independent of their prior attitudes and consequent confirmation bias. Objective: This study aimed to investigate confirmation bias in mental health-related information search, particularly (1) if high confidence worsens confirmation bias, (2) if social tags eliminate the influence of prior attitudes, and (3) if people successfully distinguish high and low source credibility. Methods: In total, 520 participants of a representative sample of the German Web-based population were recruited via a panel company. Among them, 48.1% (250/520) participants completed the fully automated study. Participants provided prior attitudes about antidepressants and psychotherapy. We manipulated (1) confidence in prior attitudes when participants searched for blog posts about the treatment of depression, (2) tag popularity -either psychotherapy or antidepressant tags were more popular, and (3) source credibility with banners indicating high or low expertise of the tagging community. We measured tag and blog post selection, and treatmentefficacy ratings after navigation. Results: Tag popularity predicted the proportion of selected antidepressant tags (beta=.44, SE 0.11; P<.001) and blog posts (beta=.46, SE 0.11; P<.001). When confidence was low (-1 SD), participants selected more blog posts consistent with prior attitudes (beta=-.26, SE 0.05; P<.001). Moreover, when confidence was low (-1 SD) and source credibility was high (+1 SD), the efficacy ratings of attitude-consistent treatments increased (beta=.34, SE 0.13; P=.01). Conclusions: We found correlational support for defense motivation account underlying confirmation bias in the mental health-related search context. That is, participants tended to select information that supported their prior attitudes, which is not in line with the current scientific evidence. Implications for presenting persuasive Web-based information are also discussed. Trial registration: ClinicalTrials.gov NCT03899168; https://clinicaltrials.gov/ct2/show/NCT03899168 (Archived by WebCite at http://www.webcitation.org/77Nyot3Do).
... The second influence on confirmation bias occurs when people face cues from socially aggregated information on the web [20][21][22][23][24][25]. Cues indicating socially aggregated information include star ratings, likes, retweet counts, or social tags. ...
Preprint
BACKGROUND In health-related, Web-based information search, people should select information in line with expert (vs nonexpert) information, independent of their prior attitudes and consequent confirmation bias. OBJECTIVE This study aimed to investigate confirmation bias in mental health–related information search, particularly (1) if high confidence worsens confirmation bias, (2) if social tags eliminate the influence of prior attitudes, and (3) if people successfully distinguish high and low source credibility. METHODS In total, 520 participants of a representative sample of the German Web-based population were recruited via a panel company. Among them, 48.1% (250/520) participants completed the fully automated study. Participants provided prior attitudes about antidepressants and psychotherapy. We manipulated (1) confidence in prior attitudes when participants searched for blog posts about the treatment of depression, (2) tag popularity —either psychotherapy or antidepressant tags were more popular, and (3) source credibility with banners indicating high or low expertise of the tagging community. We measured tag and blog post selection, and treatment efficacy ratings after navigation. RESULTS Tag popularity predicted the proportion of selected antidepressant tags (beta=.44, SE 0.11; P<.001) and blog posts (beta=.46, SE 0.11; P<.001). When confidence was low (−1 SD), participants selected more blog posts consistent with prior attitudes (beta=−.26, SE 0.05; P<.001). Moreover, when confidence was low (−1 SD) and source credibility was high (+1 SD), the efficacy ratings of attitude-consistent treatments increased (beta=.34, SE 0.13; P=.01). CONCLUSIONS We found correlational support for defense motivation account underlying confirmation bias in the mental health–related search context. That is, participants tended to select information that supported their prior attitudes, which is not in line with the current scientific evidence. Implications for presenting persuasive Web-based information are also discussed. CLINICALTRIAL ClinicalTrials.gov NCT03899168; https://clinicaltrials.gov/ct2/show/NCT03899168 (Archived by WebCite at http://www.webcitation.org/77Nyot3Do)
... To realize a TRM that searches for popular and semantically resonant (topically relevant) tags, we make use of a strategy that has been conceptually proposed (but not empirically evaluated) by Seitlinger, Ley, and Albert (2013). First simulation-based analyses of large-scale social tagging datasets (Kowald et al., 2014) have shown this strategy to be successful in modeling and predicting users' tag choices. ...
Article
Full-text available
Creative group work can be supported by collaborative search and annotation of Web resources. In this setting, it is important to help individuals both stay fluent in generating ideas of what to search next (i.e., maintain ideational fluency) and stay consistent in annotating resources (i.e., maintain organization). Based on a model of human memory, we hypothesize that sharing search results with other users, such as through bookmarks and social tags, prompts search processes in memory, which increase ideational fluency, but decrease the consistency of annotations, e.g., the reuse of tags for topically similar resources. To balance this tradeoff, we suggest the tag recommender SoMe, which is designed to simulate search of memory from user-specific tag-topic associations. An experimental field study (N = 18) in a workplace context finds evidence of the expected tradeoff and an advantage of SoMe over a conventional recommender in the collaborative setting. We conclude that sharing search results supports group creativity by increasing the ideational fluency, and that SoMe helps balancing the evidenced fluency-consistency tradeoff. © 2017 Paul Seitlinger, Tobias Ley, Dominik Kowald, Dieter Theiler, Ilire Hasani-Mavriqi, Sebastian Dennerlein, Elisabeth Lex, and Dietrich Albert. Published by Taylor and Francis.
... In the years since, a substantial literature on the dynamics of tagging behavior has developed. Research has covered topics as diverse as the relationship between social ties and tagging habits (Schifanella et al., 2010), vocabulary evolution (Cattuto, Baldassarri, et al., 2007), mathematical and multi-agent modeling of tagging behaviors (Lorince & Todd, 2013;Cattuto, Loreto, & Pietronero, 2007), identification of expert 7 taggers (Noll et al., 2009;Yeung et al., 2011), emergence of consensus among taggers (Halpin et al., 2007;Robu et al., 2009), and tag recommendation (Jäschke et al., 2007;Seitlinger et al., 2013), among others. ...
Chapter
Full-text available
As an example of exploring human memory cue use in an ecologically valid context, we present ongoing work to examine the “memory cue hypothesis” in collaborative tagging. In collaborative tagging systems, which allow users to assign freeform textual labels to digital resources, it is generally assumed that tags function as memory cues that facilitate future retrieval of the resources to which they are assigned. There is, however, little emprirical evidence demonstrating that this is in fact the case. Employing large-scale music listening and tagging data from the social music website Last.fm as a case study, we present a set of time series and information theoretic analytic methods we are using to explore how patterns of content tagging and interaction support or refute the hypothesis that tags function as retreival cues. Early results are, on average, consistent with the hypothesis. There is an immediate practical application of this work to those working with collaborative tagging systems (are user motivations what we think they are?), but our work also comprises contributions of interest to the cognitive science community: First, we are expanding our understanding of how people generate and use memory cues “in the wild”. Second, we are enriching the “toolbox” available to cognitive scientists for studying cognition using large-scale, ecologically valid data that is latent in the logged activity of web users.
Conference Paper
Full-text available
Social Tagging is a recent widespread phenomenon on the Web where people assign labels (tags) to Web resources. It has been hypothesized to support collaborative sensemaking. In this paper, we examine some of the cognitive mechanisms assumed to underlie sensemaking, namely social imitation. In line with the semantic imitation model of Fu et al., we assume that implicit processing can be understood as a semantic reconstruction of gist. Our model contrasts this process with a recall of tags from an explicit verbatim memory trace. We tested this model in an experimental study in which after the search task students had to generate tags themselves. We exposed their answers to a multinomial model derived from Fuzzy Trace Theory to obtain independent parameter estimates for the processes of explicit recall, semantic gist reconstruction and familiarity-based recall. A model that assumes all processes are at play explains the data well. Similar to results of our previous study, we find an influence of search intentions on the two processes. Our results have implications for interface and interaction design of social tagging systems, as well as for tag recommendation in these environments.
Article
Full-text available
An overview of a simulation model of human memory is presented. The model assumes: (1) that only episodic traces are stored in memory, (2) that repetition produces multiple traces of an item, (3) that a retrieval cue contacts all memory traces simultaneously, (4) that each trace is activated according to its similarity to the retrieval cue, and (5) that all traces respond in parallel, the retrieved information reflecting their summed output. The model has been applied with success to a variety of phenomena found with human subjects in frequency and recognition judgment tasks, the schema-abstraction task, and paired-associate learning. Application of the model to these tasks is briefly summarized.
Conference Paper
Full-text available
Motivation -- We analyzed the importance of social tags during an information search in a social software system. In particular, we examined the effects of tags on users' implicit/automatic and explicit/controlled memory processes. Research approach -- An experiment was conducted in which 48 students took part. By means of process dissociation and a multinomial model we tested our dual-process model (implicit vs. explicit) of social tagging. Findings/Design -- We conclude that implicit and explicit processes can be dissociated and that tags are important cues during an information search: they leave robust explicit memory representations. Research limitations/Implications -- A laboratory setting was chosen to care for conclusive findings. Our methods may have to be applied in the natural field to increase external validity. Originality/Value -- This study directly measures cognitive processes of social tagging and uses an empirical as well as experimental approach to the research questions. Take away message -- Generative Models of social tagging would benefit from incorporating a dual-process account, where formalizations of signal-detection-theory and markov-models would enable the integration of automatic and controlled processes, respectively.
Conference Paper
Full-text available
We describe a semantic imitation model of social tagging that integrates formal representations of semantics and a stochastic tag choice process to explain and predict emergent behavioral patterns. The model adopts a probabilistic topic model to separately represent external word-topic and internal word-concept relations. These representations are coupled with a tag-based topic inference process that predicts how existing tags may influence the semantic interpretation of a document. The inferred topics influence the choice of tags assigned to a document through a random utility model of tag choices. We show that the model is successful in explaining the stability in tag proportions across time and power-law frequency-rank distributions of tag co-occurrences for semantically general and narrow tags. The model also generates novel predictions on how emergent behavioral patterns may change when users with different domain expertise interact with a social tagging system. The model demonstrates the weaknesses of single-level analyses and highlights the importance of adopting a multi-level modeling approach to explain online social behavior.
Article
Full-text available
Collaborative tagging systems allow users to assign keywords - so called “tags” - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurrences. We show that both FolkRank and collaborative filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender.
Conference Paper
Nomadic inquiry may benefit from tagging when used for educational purposes to support reflection and annotation during data collection. To that end we created Zydeco, a mobile system to scaffold learners through the science inquiry process in and out of the classroom, and tested it in a museum with 42 middle school students. Students report that tags encouraged reflection and annotation during data collection, suggesting that tagging can be used to support nomadic inquiry. From this work we present some emerging design recommendations for constructing similar systems.
Article
Social tagging on online portals has become a trend now. It has emerged as one of the best ways of associating metadata with web objects. With the increase in the kinds of web objects becoming available, collaborative tagging of such objects is also developing along new dimensions. This popularity has led to a vast literature on social tagging. In this survey paper, we would like to summarize different techniques employed to study various aspects of tagging. Broadly, we would discuss about properties of tag streams, tagging models, tag semantics, generating recommendations using tags, visualizations of tags, applications of tags and problems associated with tagging usage. We would discuss topics like why people tag, what influences the choice of tags, how to model the tagging process, kinds of tags, different power laws observed in tagging domain, how tags are created, how to choose the right tags for recommendation, etc. We conclude with thoughts on future work in the area.