Enhancing SNS Profile Writing with a Search-Based Assistant System Kousuke Nagase1 , Hideo Joho1 1 University of Tsukuba, Tennodai 1 1 1, Tsukuba, Ibaraki, Japan Abstract In Social Networking Services (SNS), user profiles, which often consist of an image, texts, and other items, have an important role to connect with other users. However, in a preliminary study with 3,193 sample profiles on Twitter, we found that the average length of profile texts was 40 characters (đ‘†đ· = 32.52) where the maximum length is 160. This suggests that many SNS users are missing potential opportunities to expand their social network due to the short profile texts. Therefore, we proposed a search-based interactive system to support the writing of profile texts in SNS. The proposed system was designed to dynamically search for similar profile texts while users were typing their profile so that they can get new ideas such as what to write or how to express. We evaluated the effect of the proposed system by a user study with 24 participants, and found that the proposed system enabled participants to significantly increase the length of written profile texts (+92.5% on average), compared to a baseline system with no assistance. Keywords Social Network, User Profile, Writing Assistant, Dynamic Search, User Study 1. Introduction 1.1. Research Background Social Networking Services (SNS) have exploded in pop- ularity. According to a survey by Metaxas et al. (2014), self-expression and networking were the two main pur- poses for using Twitter with the proportion of 35.7% and 33.2%, respectively [1]. For the self-expression and net- working on SNS, the user profile is essential to establish new connections with other users [2, 3]. For example, Figure 1: Distribution of the number of characters in the a study reported that longer self-description texts were profile text of Twitter accounts (𝑁 = 3, 193, 𝑀 𝑒𝑎𝑛 = 40, perceived to be more trustworthy [4]. In an experimental đ‘†đ· = 32.52) study by Counts et al. (2009), “Quotes” and “About” were found to be useful in expressing personality traits [5]. However, many SNS users do not have a rich profile text. Figure 1 shows the distribution of the number of characters in the profile text of 3,193 Twitter accounts their profile text in social networking. This observation who are deemed to associate with one of the major univer- led us to develop and evaluate a mechanism that enables sities in Japan. The accounts were manually collected by SNS users to generate richer profile texts. one of the authors from Twitter lists that were distributed The current work was inspired by the concept of Ob- by the associated members of the University. Figure 1 servational Learning [8] in the field of Social Psychology. shows that a large proportion of accounts uses less than In a broad sense, Observational Learning is the process half of the maximum number of characters which is 160. of learning something by observing the behaviour of oth- The average length of profile texts was 40. Even though ers. We thought that the behaviour of referring to the some of them wrote limited information intentionally profile text of other users could be regarded as a form of due to some reasons like a privacy concern [6, 7], there observational learning. might be many users who can benefit from enriching 1.2. Related Works DESIRES 2021 – 2nd International Conference on Design of Experimental Search Information REtrieval Systems, September Research related to the present study includes writing 15–18, 2021, Padua, Italy support for different types of texts, which consist of nov- " nagase.kosuke.sw@alumni.tsukuba.ac.jp (K. Nagase); els, scientific paper, sentences written in a foreign lan- hideo@slis.tsukuba.ac.jp (H. Joho) © 2021 Copyright for this paper by its authors. Use permitted under Creative guage [9, 10, 11]. Roemmele, et al. developed a system Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings http://ceur-ws.org ISSN 1613-0073 CEUR Workshop Proceedings (CEUR-WS.org) to support the creation of story texts by suggesting the completion of the next sentence from a previously cre- writing. And, finally, in Section 6, we conclude the paper ated text [9]. Once the user has decided on the theme and with future work. vision of the story, he or she can write specific sentences with the help of the program. Kinnunen et al. developed a system that checks for criteria such as “are keywords 2. Proposed system that occur frequently in the abstract also used in the ti- This section describes the major components of the pro- tle” to help users write readable and consistent scientific posed system: corpus, user interface, and back-end search papers [10]. system. Ellison, et al. [2] conducted an interview study with users of an online dating service and found that many participants used other users’ profile information to find 2.1. Corpus out what they should pay attention to in constructing The first step in our work was to build a corpus which their profiles. For example, one participant stated that was then indexed and searched by the proposed writ- she avoided using a sitting posture as her icon image ing assistance system. Since the idea of observational because she had found that it was used by some users to learning indicates that users can benefit from the learn- make themselves look thinner. ing of prior examples created by other users in similar In Information Retrieval (IR), Capra, et al. proposed contexts, we decided to collect user profile texts from the search assistance system, called “Search Guide” suing the accounts that deem to have some level of association search trails [12]. Users can refer to other users’ search with our study participants: students at one of the major trails (e.g., queries issued, results clicked, pages book- universities in Japan. marked) as an example of the search behaviour. It was First, we manually collected 46 Twitter lists which found that the Search Guide can help users’ complex were created by the associated members of the university. search behaviour. Then we collected the accounts of the members of each However, there is little work on the development and collected list as well as the accounts who they follow. evaluation of tools to support the writing of profile text Finally, the data for each account, including the profile for SNS. In general, SNS profile text is much shorter than text, was automatically obtained via Twitter API. As a a story or scientific article. Therefore, we need a different result, a total of 785,531 profile texts were collected. approach from assisting users to maintain consistency Furthermore, we had two automated steps to remove in their writing or to write longer sentences efficiently profile texts for our research aim. First, as the collected [9, 10]. accounts included accounts of organisations and bot accounts, we excluded them from the search if they 1.3. Research Aim contained any of the following words. This study aims to help users identify what to write in administrator / association / booking / bot / commu- their profile text. For this aim, we proposed a system nity / closed / event / info / official / sales / shop / tel to assist users in creating SNS profile text by searching relevant profile texts created by other SNS users. More Second, it was necessary to exclude profile texts that specifically, we formulated the two research questions as were too short or did not contain enough information follows. as observational learning. We decided to exclude profile RQ1 Do people generally find it difficult to write their texts with less than 40 characters from the search. In the SNS profile text, and if so why? end, 351,754 profile texts were included in the corpus. RQ2 Will the presentation of profile texts written by 2.2. User Interface other users with similar interests help SNS users to write a longer profile text? The UI of the proposed system is shown in Figure 2. The UI consists of three main areas: Edit Area, Search Result Area, and Keep Area. When a user edits a profile text 1.4. Paper Structure on the form in Edit Area, the system retrieves relevant The rest of the paper is structured as follows. In Section other users’ profile text and displays them in the Search 2, the proposed writing assistant system is presented. In Result Area. The user can use the search results to refer Section 3, we describe the user study to evaluate the ef- to and rewrite his or her profile text. The search results fectiveness of the proposed system. In Section 4 presents were dynamically updated as the texts in Edit Area are the experimental results. In Section 5, we discuss the changed. Therefore, we provided an option to “keep” main findings and their implications on the SNS profile profile texts you find helpful in the Keep Area. Finally, Figure 2: UI of the proposed system Figure 3: A sequence diagram of the proposed system there was a button at the bottom of the Edit Area to file server (Nginx), HTTP Server (RESTful API Server), indicate the completion of the writing task during the and Elasticsearch. Each component was deployed as a user study. Pod in an on-premises Kubernetes cluster. When a user During the experiment, a controlled UI was also devel- accesses the URL of the proposed system front-end UI, oped where the overall look was identical to the proposedthe static file server first serves page contents such as UI. However, the controlled UI did not have the Search HTML, CSS and JavaScript. After that, the interaction Result Area and Keep Area. events on the page and the profile text created by the user are sent to the API server and stored in the server’s file 2.3. Back-End Search System system. Finally, profile texts are retrieved from the corpus by Elasticsearch. We added some plugins to Elasticsearch Figure 3 is a sequence diagram of the proposed system. to tokenize Japanese text and configured Elasticsearch to The proposed system consists of three components: Static rank documents by Okapi BM25 [13]. Since we used a manually constructed non-standard Table 1 corpus of SNS profile texts in our experiment, we tested Answers to “Please answer only if you have used SNS before: the performance of the back-end search system to en- Have you ever had trouble writing your profile text?” (5-point sure that it can retrieve relevant texts. Twenty simulated scale from “1. Never” to “5. Every time I cannot write well”, queries were manually created by using partial profile 24 participants) texts, the top 200 documents were retrieved by the back- Answer Number of participants end search system, and their relevance was assessed with 5 (Every time I cannot write well) 1 (4%) graded relevance by the authors. The MAP was 0.589 4 10 (42%) and nDCG@20 was 0.557. Although this was an informal 3 4 (17%) system evaluation, the results were sufficiently promising 2 7 (29%) for our research aim. 1 (Never) 2 (8%) 3. Experiments 4. Results To evaluate the effectiveness of the proposed system, a user study was conducted with 24 participants who used A total of 24 profile texts were generated in the experi- the interactive writing assistant system which indexed ment and used for analyses. the custom collection of Twitter profile texts as described in 2.1. The user study was approved by the ethics com- 4.1. Profile Writing Experience mittee of the Faculty of Library, Information and Media Science, Univerity of Tsukuba (No. 20-7). The experiment To answer RQ1, we investigated participants’ profile writ- consisted of a pre-questionnaire, a profile text writing ing experience. We prepared a questionnaire that asked: task and a post-questionnaire. Due to COVID-19, the call "Have you ever had trouble writing in the self-description for participants and all tasks were conducted online. text of your SNS profile? The breakdown of the answers (on a five-point scale from “1. Never” to “5. Every time I cannot write well”) is shown in Table. 1. Only 8% of the 3.1. Participants participants answered “1. Never”, indicating that having Of 24 participants, 14 (58%) were female and 10 (42%) a difficult experience in writing their SNS profile text is were male. All participants were undergraduate students common. The average of the answers was 3.04 and the in the age group between 18 and 22. Their academic back- standard deviation was 1.12. ground varied among Library and Information Science A follow-up question was asked only for those par- (13), Computer Science (2), Medicine (2), Social Sciences ticipants who had experienced difficulties (Answer 2 to (2), Mathematics (1), Engineering (1), Disability Science 5) in writing their profile text: “What is the reason for (1), Education (1) and Media Science (1). this?” The options of answers and the results are shown in Table 2. The most common answer was “I could think 3.2. Profile Text Writing Task of many things I could write about, but I didn’t know what to write about in particular” (9 of 18 participants Participants were asked to write a profile text in our user answered). The second most common answer was “I study. Participants were randomly assigned to one of two didn’t feel I had anything to write about” and “I wanted groups: Control and Experimental. Twelve participants to remain anonymous, so I had to be careful not to in- in the Experimental group created a profile text using the clude any personal information” (7 of 18). Again, these proposed system, and twelve participants in the Control responses support our motivation that many SNS can group created a profile text without using the suggestion benefit from writing assistant tools to enrich their profile function. They were also instructed to create a profile texts, although some users intentionally provided limited text under the following scenario. information to keep their privacy. “To increase online communication between students at the university, the university asked all students to create a 4.2. Profile Texts Twitter account. What kind of profile text would you like to create for your SNS account for the campus life?” To answer the research question RQ2, we compare the Since our collection was focused on university-related distribution of the number of characters in the profile user profiles, we designed the scenario as above to avoid text created between the two groups. Firstly, the number zero-match results in the Search Results area during the of characters in the profile text created by each group in profile writing task. descending order is compared in Figure 4. As can be seen, the experimental group tended to have more characters Table 2 Please answer this question only if you answered in the previous question that you have had trouble writing your profile text. What was the reason? (multiple answers possible, 18 respondents) Selected reason Number of participants “I could think of lots of things I could write about, but didn’t know what to write about in particular” 9 (50%) “I didn’t feel I had anything to write about” 7 (39%) “I wanted to remain anonymous, so I had to be careful not to include any personal information” 7 (39%) "I was concerned that I might come across as self-conscious if I wrote long sentences" 6 (33%) “I thought it would be strange if I wrote something different from other users around me” 2 (11%) Others (e.g. “I didn’t know how to introduce myself”) 2 (11%) Figure 5: Distribution of the number of characters in the cre- ated profile text - comparison by boxplot (N=12) Figure 4: Distribution of the number of characters in the cre- ated profile text (N=12) ing method. It is a two-tailed test and the null hypothesis is rejected at 5% level of significance. Since the sample size in this study is small (12 participants for each groups), in their profile texts. we thought it necessary to also focus on the effect size as Next, we compared it using the boxplot and the results well as the p-value [14]. The effect size 𝑟 for the Mann- are shown in Figure 5. It can be seen that the quartiles Whitney U test can be calculated from the test statistic and the minimum and maximum values are larger in the U and the sample size and satisfies −1.00 ≀ 𝑟 ≀ 1.00 experimental group. In addition, the value of the quar- [14]. The coin package [15] (1.4-1) on the CRAN package tile range is relatively larger in the experimental group. manager for R language was used to compute p-value and This indicates that the effect of increasing the number of effect size. The results of the Mann-Whitney U test are characters by using the proposed system varied across shown in Table 4. From 𝑝 < 0.0.5, there is a significant participant. The descriptive statistics values are summa- difference between the two distributions. In addition, as rized in Table 3. r-value coincides with the one for Pearson’s correlation Furthermore, a statistical test was carried out to see if coefficient [14], it can be considered as a moderate effect there was a statistical significance in the distribution of size (0.36 ≀ 𝑟 ≀ 0.67) [16]. the number of characters between the two groups. The Additionally, we analysed the time participants spent Shapiro-Wilk test was used to confirm that the distribu- during the profile writing task, and Figure 6 shows the re- tion did not follow a normal distribution for both groups, sult. It was found that the experimental group took 164.5 and thus, the Mann-Whitney U test was used as the test- seconds longer than the control group on the median Table 3 The descriptive statistics values of the distribution of the number of characters Min. 1st Quart. Central 3rd Quart. Max. Quart. Range Mean SD experimental system 25.00 43.75 60.00 81.00 119.00 37.25 64.33 29.48 control system 13.00 16.00 25.00 35.75 92.00 19.75 33.42 25.23 Table 4 Table 5 Results of a Mann-Whitney U-test on the distribution of the Breakdown of “Items that participants did not intend to write number of characters in the profile texts for both groups but actually wrote” (multiple answers) in the experimental group. p-value Z statistics Effect Size 𝑟 Effect Size [16] Item name Number of participants 0.04307 2.7725 0.5659342 moderate Other (Free answer. “Research Interests”, 5 “Previous Affiliation”, “Greetings”, “Awards Received”, “Hometown”) URLs (to other social networking sites or blog) 4 Hobbies and Interests 3 Age 2 Name/Nickname/What you are called 1 tions”, etc.), followed by “URLs to their social networking sites or blog”, and “Hobbies and Interests”. While RQ2 suggests that the proposed system allowed participants to write longer texts in the SNS profile, the answers to this questionnaire give more details about how those longer texts enriched the profile texts that were otherwise shorter and potentially less diverse. 5. Discussion This section highlights the main findings from our study and discusses their implication on supporting profile writ- Figure 6: Time taken by the participants to write their own ing and the limitation of the study. profile text [s] (N=12) First of all, we discuss the findings on RQ1 “Do peo- ple generally find it difficult to write their SNS profile text, and if so why?” The outcome of the questionnaire suggests that 44% of participants found some level of dif- comparison, suggesting that participants in the experi- ficulty in writing profile texts. This is a large proportion mental group spent more time on profile writing. given the scale of SNS user populations. The cause of difficulty varied from the lack of ideas to uncertainty of 4.3. Items in Profile Texts self-disclosure and self-impression, to a concern of pri- vacy. This finding supports our intuition on the need for We asked the following questions in the post question- assistance in writing profile texts in SNS. naire: “What did you have in mind when you started RQ2 was “Will the presentation of profile texts written writing your profile text?” (A) and “What was written in by other users with similar interests help SNS users to the final profile text?” (B). In both questions, participants write a longer profile text?” Participants managed to selected their answers from the same list of possible an- write significantly longer profile texts with the proposed swers, including “Affiliation” and “Hobbies”. We counted system where existing profile texts were dynamically the number of increase between what participants “In- retrieved and presented to the writing UI. The follow- tended to Write” (A) and what they “Actually Wrote” (B). up questionnaire showed that participants obtained the The result is summarized in Table 5. The most common ideas of adding their interests and relevant URLs to the answer was “Others” (“Research Interests”, “Past Affilia- profile texts in the proposed system. profiles written by the proposed system can lead to a bet- Therefore, providing a learning opportunity based on ter extension of social networks than existing profiles or existing users with similar interests seems to be a promis- profiles written by other methods. Furthermore, search- ing method to help SNS users to enrich their profile texts. based observational learning seems versatile enough to Unlike the assistance system in academic writing or cre- apply to other domains, and thus, the effectiveness of the ative writing[9, 10], the profile writing seems to benefit proposed system in other writing tasks such as product from the prior examples of "similar account" since the review writing should also be an interesting research main aim of SNS is to connect with people with similar direction. Finally, how to achieve a good balance be- interests. Given that online communities are diverse, our tween privacy and effective profile is yet another impor- approach of retrieving profile texts from similar accounts tant research question to be addressed in future work. seems to have an advantage over a fixed list of items to From a system design perspective, how to integrate the include in the profile. assistance function to the operational SNS needs to be As for the limitation of our work, first, participants of examined [18]. our user study were recruited from a single university although their academic background varied. Therefore, a similar effect might not appear in other SNS user popula- tions (e.g., different age groups or occupations). Second, this study did not verify whether the profile text created by the proposed system is indeed effective at expand- ing social network. Third, as pointed out in previous research[17], user privacy also needs to be considered in supporting the creation of user-generated content, in- cluding profile text. Finally, this study did not investigate whether the ranking algorithm of the back-end search system affected the user experience. 6. Conclusion and Future Work Based on our preliminary observation that the average length of SNS profile texts was not nearly as long as it could be, we developed a search-based profile writing support tool. The basic idea of our proposed system was to provide users with potential ideas about what to write and how to express by offering profile texts written by other users with similar interests. A user study was car- ried out with 24 participants to evaluate the effectiveness of the proposed system. The experimental results show that the proposed system can enhance the profile writ- ing task by allowing users to include more items in the profile texts leading to longer and richer contents. The results of questionnaires also indicate that one of the reasons for short profile texts is due to the difficulty in writing profile texts, supporting the motivation of our work, while some users preferred to be anonymous with limited profile content. Nevertheless, this work suggests that the proposed system will be helpful for those who would like to effectively extend their social network by richer profile contents. This paper demonstrated that search-based assistance was effective for SNS profile writing of a particular uni- versity student group. Future work should investigate the effectiveness with other university student groups as well as other population groups (e.g., professionals). Further work is also desirable to examine whether the References [10] T. Kinnunen, H. Leisma, M. Machunik, T. Kakkonen, J.-L. LeBrun, SWAN - scientific writing AssistaNt. [1] P. T. Metaxas, E. Mustafaraj, K. Wong, L. Zeng, a tool for helping scholars to write reader-friendly M. O’Keefe, S. Finn, Do Retweets indicate Inter- manuscripts, in: Proceedings of the Demonstra- est, Trust, Agreement? (Extended Abstract), CoRR tions at the 13th Conference of the European Chap- abs/1411.3 (2014). URL: http://arxiv.org/abs/1411. ter of the Association for Computational Linguis- 3555. arXiv:1411.3555. tics, Association for Computational Linguistics, Avi- [2] N. Ellison, R. Heino, J. Gibbs, Managing Im- gnon, France, 2012, pp. 20–24. URL: https://www. pressions Online: Self-Presentation Processes in aclweb.org/anthology/E12-2005. the Online Dating Environment, Journal of [11] M.-H. Chen, S.-T. Huang, H.-T. Hsieh, T.-H. Kao, Computer-Mediated Communication 11 (2017) J. S. Chang, FLOW: A first-language-oriented writ- 415–441. URL: https://doi.org/10.1111/j.1083-6101. ing assistant system, in: Proceedings of the ACL 2006.00020.x. doi:10.1111/j.1083-6101.2006. 2012 System Demonstrations, Association for Com- 00020.x. putational Linguistics, Jeju Island, Korea, 2012, pp. [3] S. T. Tong, E. F. Corriero, K. A. Wibowo, T. W. Makki, 157–162. URL: https://www.aclweb.org/anthology/ R. B. Slatcher, Self-presentation and impressions of P12-3027. personality through text-based online dating pro- [12] R. Capra, J. Arguello, A. Crescenzi, E. Vardell, Dif- files: A lens model analysis, New Media & Society ferences in the use of search assistance for tasks 22 (2020) 875–895. of varying complexity, in: Proceedings of the [4] X. Ma, J. T. Hancock, K. Lim Mingjie, M. Naa- 38th International ACM SIGIR Conference on Re- man, Self-disclosure and perceived trustworthi- search and Development in Information Retrieval, ness of airbnb host profiles, in: Proceedings of SIGIR ’15, Association for Computing Machinery, the 2017 ACM Conference on Computer Supported New York, NY, USA, 2015, p. 23–32. URL: https: Cooperative Work and Social Computing, CSCW //doi.org/10.1145/2766462.2767741. doi:10.1145/ ’17, Association for Computing Machinery, New 2766462.2767741. York, NY, USA, 2017, p. 2397–2409. URL: https: [13] S. Robertson, S. Walker, S. Jones, M. M. Hancock- //doi.org/10.1145/2998181.2998269. doi:10.1145/ Beaulieu, M. Gatford, Okapi at trec-3, in: Overview 2998181.2998269. of the Third Text REtrieval Conference (TREC- [5] S. Counts, K. Stecher, Self-presentation of person- 3), Gaithersburg, MD: NIST, 1995, pp. 109–126. ality during online profile creation, in: Conference: URL: https://www.microsoft.com/en-us/research/ Proceedings of the Third International Conference publication/okapi-at-trec-3/. on Weblogs and Social Media, ICWSM 2009, 2009. [14] M. Tomczak, E. Tomczak, The need to report effect [6] H. Krasnova, S. Spiekermann, K. Koroleva, T. Hilde- size estimates revisited. an overview of some rec- brand, Online social networks: why we disclose, ommended measures of effect size 21 (2014) 19–25. Journal of Information Technology 25 (2010) 109– [15] H. Torsten, H. Kurt, M. Van de Wiel, Z. Achim, 125. URL: https://doi.org/10.1057/jit.2010.6. doi:10. Implementing a class of permutation tests: The coin 1057/jit.2010.6. package, Journal of Statistical Software 28 (2008). [7] F. Stutzman, J. Kramer-Duffield, Friends only: doi:10.18637/jss.v028.i08. Examining a privacy-enhancing behavior in face- [16] R. Taylor, Interpretation of the correlation coeffi- book, in: Proceedings of the SIGCHI Conference cient: A basic review, Journal of Diagnostic Medical on Human Factors in Computing Systems, CHI Sonography 6 (1990) 35 – 39. ’10, Association for Computing Machinery, New [17] Y. Fang, A. Godavarthy, H. Lu, A utility maximiza- York, NY, USA, 2010, p. 1553–1562. URL: https: tion framework for privacy preservation of user //doi.org/10.1145/1753326.1753559. doi:10.1145/ generated content, in: Proceedings of the 2016 1753326.1753559. ACM International Conference on the Theory of [8] A. Bandura, Observational Learning, 2 Information Retrieval, ICTIR ’16, Association for ed., Macmillan Reference USA, New Computing Machinery, New York, NY, USA, 2016, York, NY, 2004, pp. 482–484. URL: https: p. 281–290. URL: https://doi.org/10.1145/2970398. //link.gale.com/apps/doc/CX3407100173/GVRL? 2970417. doi:10.1145/2970398.2970417. u=cuny_hunter&sid=GVRL&xid=369c6e06, topic [18] G. Dworman, S. Rosenbaum, Helping users to overview. use help: Improving interaction with help sys- [9] M. Roemmele, A. S. Gordon, Creative help: A story tems, in: CHI ’04 Extended Abstracts on Human writing assistant, in: International Conference on Factors in Computing Systems, CHI EA ’04, 2004, Interactive Digital Storytelling, Springer, 2015, pp. p. 1717–1718. URL: https://doi.org/10.1145/985921. 81–92. 986198. doi:10.1145/985921.986198.