{"id":5382,"date":"2022-03-07T07:59:21","date_gmt":"2022-03-07T07:59:21","guid":{"rendered":"https:\/\/precog.iiit.ac.in\/blog\/?p=5382"},"modified":"2022-03-07T08:13:10","modified_gmt":"2022-03-07T08:13:10","slug":"up-elections-22-midpoint-melodrama","status":"publish","type":"post","link":"https:\/\/precog.iiit.ac.in\/blog\/?p=5382","title":{"rendered":"Midpoint Melodrama: UP Political Twitter Halfway through Polling Phases"},"content":{"rendered":"\n

We examined the use of Twitter by 10426 politicians from Uttar Pradesh, across all levels of seniority, midway into the phases of polling in the Uttar Pradesh elections of 2022, starting January 1, 2022, and up until March 1, 2022. We summarize here our key findings by examining four key questions.<\/p>\n\n\n\n

How does Twitter relate to Urbanization and Literacy?<\/h2>\n\n\n\n

To address the first question, we examined the number of urban residents by location, and levels of literacy, and find there is a statistically significant relationship between both the number (and percentage) or urban residents and the likelihood that politicians in that area use Twitter, as well as with the level of literacy and the likelihood of tweeting. We removed Lucknow district from the equations we ran, since it is an outlier being the capital where most parties have a number of listed post holders.<\/p>\n\n\n\n

We see some variation \u2014 for instance, the district with the highest urban populations \u2013 Ghaziabad, adjoining Delhi, and Kanpur, both have fewer politicians online than Varanasi, the Prime Minister\u2019s constituency, which has had a lot of mid- to lower-level politicians go online, and Allahabad \/ Prayagraj, which is a politically important district in the state, and home to several key politicians from across parties.<\/p>\n\n\n\n

\"\"
Figure 1: Number of urban residents in a district correlated with the number of politicians from that district active on Twitter<\/em>.<\/figcaption><\/figure>\n\n\n\n

Taking the number of politicians on Twitter as the dependent variable and the urban population of the district as the independent variable,and found a strong correlation between the 2 with an R value of 0.61. The coefficient \ud835\udefd1 <\/sub>was found to be significantly different from 0 with p < 0.05 (see Appendix Table 1).<\/p>\n\n\n\n

\"\"
Figure 2: Percentage of urban residents in a district correlated with the number of politicians from that district active on Twitter<\/em>.<\/figcaption><\/figure>\n\n\n\n

When we ran the same regression to correlate the percentage of urban residents to the number of politicians active on Twitter, again we found a strong statistically significant (p<0.05) relationship between the two variables with an R value of 0.37. There are outliers. On the lower end, we see that Gautam Buddha Nagar (Noida) has a smaller share of politicians active online (partly because of the cross-listing with Delhi) whereas Gorakhpur, an overwhelming majority rural district has a high number of politicians active on Twitter. This again can be attributed to CM Yogi Adityanath, who contests from the district. Please see Appendix 2 for details.<\/p>\n\n\n\n

We see the same relationship between the number of literate persons in a district and the number of politicians. The relationship here is the strongest, statistically significant (p<0.05) with an R value of 0.78. Figure 3 below shows us a visualization of the districts. Again, we see that Varanasi is an outlier, for the reasons outlined above. Please see Appendix 3 for details.<\/p>\n\n\n\n

\"\"
Figure 3: Number of literate residents in a district correlated with the number of politicians from that district active on Twitter<\/em>.<\/figcaption><\/figure>\n\n\n\n

As a sanity check we ran the same regression on the share of literate persons in a district, we again find a statistically significant relationship (p<0.05) with a strong relationship of rate of literacy with the n of politicians on Twitter at an R value of 0.78. Please see Appendix 4 for details.<\/p>\n\n\n\n

\"\"
Figure 4: Percentage of literate residents in a district correlated with the number of politicians from that district active on Twitter<\/em>.<\/figcaption><\/figure>\n\n\n\n

Where\u2019s the Action?<\/h2>\n\n\n\n

To detail these findings, we detail the data by district. Using a crude method of looking at the number of active politicians and the rate at which they get retweeted, we examined the districts in which one or another party had a clear Twitter dominance. We restricted our analysis to those districts that had 50 or more active politicians online. The districts which had a clear BJP Twitter advantage (where the local networks of politicians on Twitter were larger, at least two of the top three accounts belonged to that party, and the party was more active on social media) were Ghaziabad, Amethi, Mathura, Barabanki, Kaushambi, Gorakhpur. The districts where the Samajwadi Party had a clear advantage were Banda, Fatehpur, Etawah, Prayagraj (Allahabad), and Azamgarh. The districts where the Twitter battles were evenly matched across multiple parties were Kannauj, Ballia, Lucknow, Sultanpur.<\/p>\n\n\n\n

District<\/strong>(min. 40 active politicians)<\/strong><\/td>Code<\/strong><\/td>SP<\/strong>Politicians<\/strong><\/td>BJP Politicians<\/strong><\/td>Other Party Politicians<\/strong><\/td>SP per- politician median Tweet count<\/strong><\/td>BJP per- politician median Tweet count<\/strong><\/td>Other party per- politician median Tweet count<\/strong><\/td><\/tr>
Agra<\/td>AGR<\/td>49<\/td>125<\/td>52<\/td>49<\/td>111<\/td>179.5<\/td><\/tr>
Aligarh<\/td>ALG<\/td>14<\/td>51<\/td>26<\/td>150<\/td>82<\/td>111<\/td><\/tr>
Prayagraj<\/td>ALH<\/td>123<\/td>84<\/td>59<\/td>100<\/td>53.5<\/td>142<\/td><\/tr>
Amethi<\/td>AMT<\/td>15<\/td>91<\/td>53<\/td>58<\/td>78<\/td>85<\/td><\/tr>
Ayodhya<\/td>AYD<\/td>28<\/td>74<\/td>14<\/td>28.5<\/td>165<\/td>162<\/td><\/tr>
Azamgarh<\/td>AZA<\/td>53<\/td>15<\/td>25<\/td>68<\/td>141<\/td>329<\/td><\/tr>
Bahraich<\/td>BAH<\/td>40<\/td>23<\/td>7<\/td>59<\/td>102<\/td>3<\/td><\/tr>
Ballia<\/td>BAL<\/td>26<\/td>33<\/td>25<\/td>165.5<\/td>115<\/td>131<\/td><\/tr>
Balrampur<\/td>BRP<\/td>12<\/td>14<\/td>24<\/td>36<\/td>108<\/td>212<\/td><\/tr>
Banda<\/td>BAN<\/td>25<\/td>27<\/td>16<\/td>105<\/td>65<\/td>84<\/td><\/tr>
Barabanki<\/td>BAR<\/td>26<\/td>61<\/td>19<\/td>40<\/td>78<\/td>63<\/td><\/tr>
Bareilly<\/td>BRL<\/td>33<\/td>32<\/td>19<\/td>34<\/td>68<\/td>157<\/td><\/tr>
Basti<\/td>BAS<\/td>21<\/td>76<\/td>28<\/td>17<\/td>120<\/td>241.5<\/td><\/tr>
Bhadohi<\/td>BDH<\/td>12<\/td>32<\/td>10<\/td>91<\/td>119.5<\/td>235<\/td><\/tr>
Chandauli<\/td>CHD<\/td>14<\/td>29<\/td>9<\/td>21<\/td>117<\/td>26<\/td><\/tr>
Deoria<\/td>DEO<\/td>33<\/td>63<\/td>17<\/td>53<\/td>97<\/td>69<\/td><\/tr>
Etawah<\/td>ETW<\/td>37<\/td>15<\/td>6<\/td>80<\/td>94<\/td>159<\/td><\/tr>
Fatehpur<\/td>FTH<\/td>34<\/td>19<\/td>7<\/td>77.5<\/td>130<\/td>128<\/td><\/tr>
Ghaziabad<\/td>GZB<\/td>23<\/td>121<\/td>47<\/td>118<\/td>211<\/td>122<\/td><\/tr>
Ghazipur<\/td>GZP<\/td>25<\/td>40<\/td>15<\/td>77<\/td>83.5<\/td>68<\/td><\/tr>
Gonda<\/td>GON<\/td>20<\/td>47<\/td>17<\/td>52<\/td>120<\/td>109<\/td><\/tr>
Gorakhpur<\/td>GOR<\/td>34<\/td>124<\/td>27<\/td>88.5<\/td>130.5<\/td>159<\/td><\/tr>
Hapur<\/td>HAP<\/td>7<\/td>31<\/td>27<\/td>44<\/td>205<\/td>199<\/td><\/tr>
Hardoi<\/td>HAR<\/td>21<\/td>53<\/td>12<\/td>59<\/td>58<\/td>98.5<\/td><\/tr>
Hathras<\/td>HAT<\/td>4<\/td>17<\/td>10<\/td>320.5<\/td>145<\/td>86<\/td><\/tr>
Jaunpur<\/td>JNP<\/td>66<\/td>100<\/td>43<\/td>90<\/td>84.5<\/td>145<\/td><\/tr>
Jhansi<\/td>JHA<\/td>26<\/td>28<\/td>26<\/td>48.5<\/td>177.5<\/td>93.5<\/td><\/tr>
Kannauj<\/td>KAN<\/td>26<\/td>26<\/td>8<\/td>109<\/td>102<\/td>97.5<\/td><\/tr>
Kanpur Dehat<\/td>KND<\/td>15<\/td>16<\/td>6<\/td>29<\/td>288.5<\/td>283<\/td><\/tr>
Kanpur Nagar<\/td>KNN<\/td>58<\/td>81<\/td>24<\/td>63<\/td>136<\/td>74.5<\/td><\/tr>
Kaushambi<\/td>KAU<\/td>7<\/td>30<\/td>7<\/td>50<\/td>138<\/td>150<\/td><\/tr>
Lucknow<\/td>LCK<\/td>442<\/td>406<\/td>226<\/td>113.5<\/td>158<\/td>147.5<\/td><\/tr>
Mathura<\/td>MAT<\/td>12<\/td>53<\/td>38<\/td>19.5<\/td>89<\/td>102.5<\/td><\/tr>
Meerut<\/td>MRT<\/td>21<\/td>77<\/td>38<\/td>96<\/td>137<\/td>197<\/td><\/tr>
Mirzapur<\/td>MIR<\/td>17<\/td>39<\/td>20<\/td>56<\/td>41<\/td>109.5<\/td><\/tr>
Moradabad<\/td>MOR<\/td>27<\/td>48<\/td>14<\/td>32<\/td>80.5<\/td>92<\/td><\/tr>
Muzaffarnagar<\/td>MUZ<\/td>13<\/td>26<\/td>30<\/td>56<\/td>213<\/td>144.5<\/td><\/tr>
Pratapgarh<\/td>PGH<\/td>22<\/td>44<\/td>14<\/td>96.5<\/td>75<\/td>19<\/td><\/tr>
Rampur<\/td>RAM<\/td>11<\/td>29<\/td>14<\/td>28<\/td>103<\/td>80<\/td><\/tr>
Saharanpur<\/td>SAH<\/td>13<\/td>42<\/td>20<\/td>60<\/td>137.5<\/td>185<\/td><\/tr>
Shahjahanpur<\/td>SHJ<\/td>15<\/td>23<\/td>12<\/td>26<\/td>85<\/td>127.5<\/td><\/tr>
Sitapur<\/td>SIT<\/td>24<\/td>28<\/td>14<\/td>28<\/td>123<\/td>144.5<\/td><\/tr>
Sonbhadra<\/td>SON<\/td>10<\/td>37<\/td>12<\/td>34.5<\/td>230<\/td>500.5<\/td><\/tr>
Sultanpur<\/td>SUL<\/td>24<\/td>30<\/td>16<\/td>30<\/td>81<\/td>101.5<\/td><\/tr>
Unnao<\/td>UNN<\/td>16<\/td>32<\/td>8<\/td>59.5<\/td>34.5<\/td>148.5<\/td><\/tr>
Varanasi<\/td>VAR<\/td>87<\/td>137<\/td>74<\/td>69<\/td>111<\/td>162.5<\/td><\/tr><\/tbody><\/table>
Table 1: Key Districts (minimum 40 active politicians on Twitter online) with the number of politicians or political workers identified, and the median rates of retweets (of original tweets) for the period 2021-01-01 to 2022-03-01.<\/figcaption><\/figure>\n\n\n\n

These data points may be skewed by the effectiveness of IT cells or small cores of supporters. It is also true that the INC\u2019s IT cell is fairly well organized and networked, but most on-the-ground analyses seem to discount its likelihood of winning seats proportionate to its social media footprint. However, these data underline the massive dominance that the BJP has over other parties on Twitter.<\/p>\n\n\n\n

District Code<\/strong><\/td>Top most followed active state politician handle from the district<\/strong><\/td>Party<\/strong><\/td>2nd<\/sup> most followed active state politician handle from the district<\/strong><\/td>Party<\/strong><\/td>3rd<\/sup> most followed active state politician handle from the district<\/strong><\/td>Party<\/strong><\/td><\/tr>
JAL<\/td>Rashmipal_86<\/td>SP<\/td>bpsvermaoffice<\/td>BJP<\/td>mohammad_ubaid_<\/td>INC<\/td><\/tr>
LAL<\/td>ArchanaPatelAD<\/td>APNA<\/td>inckuldeepnsui<\/td>INC<\/td>nitinpanthltp<\/td>BJP<\/td><\/tr>
HAM<\/td>DipakSurjeet<\/td>SP<\/td>Aryan_Vaishnav9<\/td>INC<\/td>arunodayINC<\/td>INC<\/td><\/tr>
KSH<\/td>RadheshyaSingh<\/td>SP<\/td>Sunny10113594<\/td>BJP<\/td>Bjp4shubhamsahi<\/td>BJP<\/td><\/tr>
ETA<\/td>ashishyadavmla<\/td>SP<\/td>visheshYSP<\/td>SP<\/td>AsRathoreBJP<\/td>BJP<\/td><\/tr>
CHK<\/td>BhaironMishra<\/td>BJP<\/td>KishanGupta_INC<\/td>INC<\/td>AtuleshanandM<\/td>BJP<\/td><\/tr>
FRZ<\/td>DrChandrasenBJP<\/td>BJP<\/td>Prashan25958727<\/td>SP<\/td>RohitYadav5500<\/td>SP<\/td><\/tr>
GBN<\/td>satender_awana<\/td>BJP<\/td>Sandeepsharmak7<\/td>BJP<\/td>AshuChhawri1717<\/td>BJP<\/td><\/tr>
BAH<\/td>NitishRastogi01<\/td>BJP<\/td>Shivafauji<\/td>BJP<\/td>nishanktripath1<\/td>BJP<\/td><\/tr>
MAH<\/td>yadavyogi1<\/td>SP<\/td>ManojA2Y<\/td>SP<\/td>Neerajbuddh_ASP<\/td>BSP<\/td><\/tr>
KAS<\/td>inderveshverma<\/td>BJP<\/td>ABVPVikas89<\/td>BJP<\/td>TejendraLodhi<\/td>BJP<\/td><\/tr>
AUR<\/td>AAPlogical<\/td>AAP<\/td>manju27bjp<\/td>BJP<\/td>Narendralodh73<\/td>BJP<\/td><\/tr>
BRL<\/td>sachink71656735<\/td>BJP<\/td>JabirAkhtarKhan<\/td>AIMIM<\/td>DrPramendr<\/td>BJP<\/td><\/tr>
AMR<\/td>SatyadeoPawar<\/td>BJP<\/td>VishalVermaJi00<\/td>BJP<\/td>kstanwarmp<\/td>BJP<\/td><\/tr>
HAP<\/td>anandktrbjp<\/td>BJP<\/td>ramesh4Churu<\/td>BJP<\/td>SarswatPrafful<\/td>BJP<\/td><\/tr>
KAN<\/td>dineshsngyadav<\/td>SP<\/td>poonamy49617468<\/td>SP<\/td>socialistarchna<\/td>SP<\/td><\/tr>
BIJ<\/td>Ashokkatariya9<\/td>BJP<\/td>Digvija27100456<\/td>BJP<\/td>BRBJPBIJNOR<\/td>BJP<\/td><\/tr>
KND<\/td>Up32Wale<\/td>BJP<\/td>iABHIKSHA<\/td>BJP<\/td>AnkitSinghZ<\/td>BJP<\/td><\/tr>
HAT<\/td>SharadBJPoffice<\/td>BJP<\/td>islamkhan919<\/td>SP<\/td>RamAvtarValmiki<\/td>INC<\/td><\/tr>
BAS<\/td>pal_jagdambika<\/td>BJP<\/td>Shweta4Nation<\/td>BJP<\/td>BajrangbaliMa<\/td>BJP<\/td><\/tr>
BAN<\/td>Shubham41489417<\/td>BJP<\/td>HariNMishra<\/td>BJP<\/td>AAPkaRamGupta<\/td>AAP<\/td><\/tr>
BRP<\/td>Dr_Mannan_<\/td>AIMIM<\/td>HKhan_293<\/td>INC<\/td>Vibhuonline<\/td>INC<\/td><\/tr>
AZA<\/td>amitydvsp<\/td>SP<\/td>IamShaikhAdil<\/td>AIMIM<\/td>NishantRaii<\/td>SP<\/td><\/tr>
BDH<\/td>ashutoshgyanpur<\/td>BJP<\/td>AkashDubeyBJP<\/td>BJP<\/td>ratnakarbjp<\/td>BJP<\/td><\/tr>
HAR<\/td>jeetusp<\/td>SP<\/td>bjpsaurabh12<\/td>BJP<\/td>PrachiPretesh<\/td>BJP<\/td><\/tr>
FTH<\/td>MahipalMahla<\/td>BJP<\/td>anjuydv<\/td>SP<\/td>YunusSamajwadi<\/td>SP<\/td><\/tr>
GON<\/td>gopalkagarwal<\/td>BJP<\/td>KVSinghMPGonda<\/td>BJP<\/td>BNSinghbobby<\/td>BJP<\/td><\/tr>
ALG<\/td>SatishGautamBJP<\/td>BJP<\/td>kuldeepgaurBjp<\/td>BJP<\/td>LakhendraMeena<\/td>INC<\/td><\/tr>
AMT<\/td>DeepakSinghINC<\/td>INC<\/td>BJP4Amethi<\/td>BJP<\/td>dtripathi264<\/td>BJP<\/td><\/tr>
MAI<\/td>spsunilyadav<\/td>SP<\/td>LalitMYOfficial<\/td>SP<\/td>Samajwadi_mpi<\/td>SP<\/td><\/tr>
CHD<\/td>DrMNPandeyMP<\/td>BJP<\/td>mlasadhanasingh<\/td>BJP<\/td>IshanMilki<\/td>SP<\/td><\/tr>
JHA<\/td>Socialist_arun<\/td>SP<\/td>AnuraagJhansi<\/td>BJP<\/td>pradeepjain52<\/td>INC<\/td><\/tr>
GZP<\/td>Virendra_mla<\/td>SP<\/td>manvendrabjp<\/td>BJP<\/td>rajeshysp<\/td>SP<\/td><\/tr>
GOR<\/td>myogiadityanath<\/td>BJP<\/td>AgrawalRMD<\/td>BJP<\/td>kamleshpassi67<\/td>BJP<\/td><\/tr>
KAU<\/td>BJPVinodSonkar<\/td>BJP<\/td>BabluGargBjp<\/td>BJP<\/td>prashant3k1<\/td>BJP<\/td><\/tr>
BAR<\/td>priyankaMP_BBK<\/td>BJP<\/td>upendrasinghMP<\/td>BJP<\/td>PushpendraBjpKm<\/td>BJP<\/td><\/tr>
DEO<\/td>manishagautamak<\/td>BSP<\/td>msirsiwal<\/td>INC<\/td>BirendraYdvSP<\/td>SP<\/td><\/tr>
AMB<\/td>mpriteshpandey<\/td>BSP<\/td>ankitchandelbjp<\/td>BJP<\/td>12tiwari25<\/td>AAP<\/td><\/tr>
AGR<\/td>BjpRajora<\/td>BJP<\/td>AbhilashaBJP<\/td>BJP<\/td>Rajkumarchahar9<\/td>BJP<\/td><\/tr>
MAI<\/td>yadavakhilesh<\/td>SP<\/td>SubratPathak12<\/td>BJP<\/td>RanjeetYadavSP1<\/td>SP<\/td><\/tr>
BAL<\/td>sparvindgiri<\/td>SP<\/td>upendratiwari_<\/td>BJP<\/td>virendramastmp<\/td>BJP<\/td><\/tr>
AYD<\/td>pawanpandeysp<\/td>SP<\/td>LalluSinghBJP<\/td>BJP<\/td>PanditSamarjee2<\/td>SP<\/td><\/tr>
KNN<\/td>sdPachauri1<\/td>BJP<\/td>ptopmishra<\/td>SP<\/td>manojku72692521<\/td>SP<\/td><\/tr>
BAG<\/td>Phulesavitribai<\/td>KBMP<\/td>AnilTomarBjp<\/td>BJP<\/td>RLD_Baghpat<\/td>RLD<\/td><\/tr>
ALH<\/td>Vndnason<\/td>AAP<\/td>yogita_singh13<\/td>SP<\/td>RakshaMantri<\/td>SP<\/td><\/tr>
ETW<\/td>socialistaditya<\/td>SP<\/td>kuwarprashant<\/td>SP<\/td>Samajwadi_AY<\/td>SP<\/td><\/tr>
JNP<\/td>YRBSamajwadi<\/td>SP<\/td>OsamaShaikhIND<\/td>INC<\/td>Hb_o12<\/td>BJP<\/td><\/tr>
GZB<\/td>Gen_VKSingh<\/td>BJP<\/td>druditatyagi<\/td>BJP<\/td>preeti_chobey<\/td>SP<\/td><\/tr>
LCK<\/td>CMOfficeUP<\/td>BJP<\/td>BJP4UP<\/td>BJP<\/td>samajwadiparty<\/td>SP<\/td><\/tr><\/tbody><\/table>
Table 2: Top three most followed active Twitter accounts by district (minimum 40 active politicians on Twitter online) for the period 2021-01-01 to 2022-03-01.<\/figcaption><\/figure>\n\n\n\n

Who does the party think gets the votes, Modi or Yogi?<\/h2>\n\n\n\n

We examined the number of tweets that referred to Narendra Modi and Yogi Adityanath to get a sense of who the party expects will win the elections. The results show that while Yogi Adityanath had a higher footprint early in the campaign in January, that got replaced by Modi by February, to the point where Modi is now consistently the more featured of the two leaders in terms of both the engagement by party politicians and workers, and equally importantly, by the party\u2019s main social media handle.<\/p>\n\n\n\n

\"\"
Figure 5: Line graph of the number of times Narendra Modi and Yogi Adityanath are mentioned in tweets by BJP politicians through all UP districts during the study time period. We find six events corresponding to the peaks (calculated over two day interval):
1.  Jan 6, Modi peaks for 150 crore milestone for covid vaccinations
2.  Jan 9 Yogi peaks for communal 80 vs 20 tweet about BJP\u2019s win in UP
3.  Jan 14 Yogi peaks for Magh mela, announcing contest from Gorakhpur
4.  Jan 26 Modi peaks for Republic day and UP state formation day address
5.  Feb 1 Modi peaks for virtual rallies
6.  Feb 9 Modi peaks for televised ANI interview
7.  Feb 23 Modi peaks for public gatherings in Prayagraj, Amethi, Hardoi etc<\/span><\/em><\/figcaption><\/figure>\n\n\n\n

We also checked for this pattern in the main handle for the BJP in the state \u2013 @bjp4UP. Here, we see that Modi was virtually missing from the discourse in much of January, and re-emerged only in February, and since mid-February has in fact been more important in the party\u2019s outreach than the Chief Minister.<\/p>\n\n\n\n

\"\"
Figure 6: Visualization of the number of mentions weekly of @narendramodi and @myogiadityanath by @BJP4UP handle in between Dec 31 and March 3.<\/em><\/figcaption><\/figure>\n\n\n\n

We visualized the words that appeared most commonly in the tweets of that included @narendramodi and @myogiadityanath during the study period, excluding common tweets and we found that the co-occurring tweets tell a very interesting story about the way BJP leaders and the party establishment sees the two figures in its outreach. To arrive at these, we merged synonyms (thus \u0938\u092a\u093e is merged with \u0938\u092e\u093e\u091c\u0935\u093e\u0926\u0940), we remove common words articles, common verbs (thus \u092e\u0947\u0902, \u0936\u094d\u0930\u0940, \u0914\u0930, \u0939\u0948 etc) as well as words that are purely informational (\u091a\u0941\u0928\u093e\u0935, \u091c\u0928\u0938\u092d\u093e, \u092e\u0924\u0926\u093e\u0928, \u0938\u0924\u094d\u0924\u093e etc) and words that have no political consequence in the context of the tweets (\u092a\u094d\u0930\u0926\u0947\u0936, \u0932\u094b\u0917 etc), and are left with terms that are either explicitly part of the political discourse, or are about locations of relevance.<\/p>\n\n\n\n

\"\"
Figure 7: Wordcloud visualization of co-occurring words in tweets including @myogiadityanath \u2013 size of the words proportionate to the number of mentions<\/em><\/figcaption><\/figure>\n\n\n\n

We can see that the differences between the two leaders and the tweets mentioning them are significant. While there are common themes (Kisan, Garib, Vikas) we can see that there are two striking differences. First there are differences in the locations that the two sets of tweets mention Saharanpur, Kashi (his constituency), the Yogi-centric tweets mention Gorakhpur (his constituency), Ayodhya, Muzaffarnagar.<\/p>\n\n\n\n

Second, we see that the Modi-centric tweets take aim at the familial continuity of power (through the use of \u201cparivarvaad\u201d) \u2013 aimed at both Akhilesh and Priyanka, but primarily at the former. While both leaders refer to farmers, they are a lot more central to Modi-centric messaging. Likewise while \u201cCorona\u201d and \u201cVaccine\u201d also on tweets about both leaders, the centrality of vaccine success, as well as the touting of marquee initiatives like Atmanirbhar are more seen in Modi-centric messaging.<\/p>\n\n\n\n

Finally, the Yogi-centric messaging has one overarching theme \u2014 that of sectarianism. We see a number of terms either referring to Samajwadi party in veiled references to rioters, terrorists and criminals through the use of terms like \u0905\u092a\u0930\u093e\u0927\u093f\u092f\u094b\u0902, \u0906\u0924\u0902\u0915\u093f\u092f\u094b\u0902, \u092e\u093e\u092b\u093f\u092f\u093e, \u0926\u0902\u0917\u093e\u0907\u092f\u094b\u0902, \u0938\u0941\u0930\u0915\u094d\u0937\u093e but in addition, the Yogi-centric tweets are also more likely to use words such as \u092d\u0917\u0935\u093e\u0928,  \u0930\u093e\u092e\u092d\u0915\u094d\u0924\u094b\u0902, \u0936\u093f\u0932\u093e\u0928\u094d\u092f\u093e\u0938, \u0939\u093f\u0902\u0926\u0942, \u092e\u0902\u0926\u093f\u0930 etc.<\/p>\n\n\n\n

\"\"
Figure 8: Wordcloud visualization of co-occurring words in tweets including @narendramodi \u2013 size of the words proportionate to the number of mentions<\/em><\/figcaption><\/figure>\n\n\n\n

Of all the major contenders, probably the least active on social media is the Bahujan Samaj Party, and a number of their candidates are not active on Twitter. In general, Akhilesh Yadav is far more engaged than the two key other opposition leaders \u2013 Priyanka Gandhi and Mayawati, however, Priyanka Gandhi has gradually closed the gap with Akhilesh.<\/p>\n\n\n\n

\"\"
Figure 9: Mention counts of Akhilesh Yadav, Priyanka Gandhi, and Mayawati over time.<\/figcaption><\/figure>\n\n\n\n

Appendix \/ Statistical Details<\/h2>\n\n\n\n
Slope<\/td>6.20e-05<\/td><\/tr>
Intercept<\/td>46.16<\/td><\/tr>
R value (Pearson\u2019s correlation)<\/td>0.611<\/td><\/tr>
R Squared<\/td>0.374<\/td><\/tr>
P Value<\/td>2.089e-07<\/td><\/tr>
Standard Error<\/td>1.054e-05<\/td><\/tr><\/tbody><\/table>
Table 1. Regression table for  Politicians on Twitter = \ud835\udefd0 + \ud835\udefd1 * Urban Population + \ud835\udf00\ud835\udc56<\/em><\/figcaption><\/figure>\n\n\n\n
Slope<\/td>1.67<\/td><\/tr>
Intercept<\/td>50.72<\/td><\/tr>
R value (Pearson\u2019s correlation)<\/td>0.37<\/td><\/tr>
R Squared<\/td>0.14<\/td><\/tr>
P Value<\/td>0.003<\/td><\/tr>
Standard Error<\/td>0.54<\/td><\/tr><\/tbody><\/table>
Table 2. Regression table for  Politicians on Twitter = \ud835\udefd0 + \ud835\udefd1 * Percentage Urban Population + \ud835\udf00\ud835\udc56<\/em><\/figcaption><\/figure>\n\n\n\n
Slope<\/td>7.24e-05<\/td><\/tr>
Intercept<\/td>-32.78<\/td><\/tr>
R value (Pearson\u2019s correlation)<\/td>0.78<\/td><\/tr>
R Squared<\/td>0.61<\/td><\/tr>
P Value<\/td>1.19e-13<\/td><\/tr>
Standard Error<\/td>7.52e-06<\/td><\/tr><\/tbody><\/table>
Table 3. Regression table for  Politicians on Twitter = \ud835\udefd0 + \ud835\udefd1 * Literate Population + \ud835\udf00\ud835\udc56<\/em><\/figcaption><\/figure>\n\n\n\n
Slope<\/td>2.51<\/td><\/tr>
Intercept<\/td>-84.66<\/td><\/tr>
R value (Pearson\u2019s correlation)<\/td>0.07<\/td><\/tr>
R Squared<\/td>0.61<\/td><\/tr>
P Value<\/td>0.03<\/td><\/tr>
Standard Error<\/td>1.17<\/td><\/tr><\/tbody><\/table>
Table 4. Regression table for Politicians on Twitter = \ud835\udefd0 + \ud835\udefd1 * Percentage Literate Population + \ud835\udf00\ud835\udc56<\/em><\/figcaption><\/figure>\n\n\n\n

Methodology for comparing mentions of Narendra Modi and Yogi Adityanath by BJP Politicians<\/h3>\n\n\n\n

We collected all the tweets of BJP politicians over a period of around two months (from 31st Jan 2022 to 3rd Mar 2022) and counted the number of mentions which Narendra Modi and Yogi Adityanath got. We plotted this data keeping a rolling 2-day average to capture the trends in increase and decrease of mentions and correlated the peaks with relevant events.<\/p>\n\n\n\n

\n\n\n\n

This research was conducted by Lalitha Kameswari, Jivitesh Jain, Shaurya Dewan, Aravind Narayanan, Dipanwita Guhathakurta, and Prof. Ponnurangam Kumaraguru from IIIT Hyderabad, Asmit Kumar Singh and Tushar Mohan from IIIT Delhi, and Prof. Joyojeet Pal from the University of Michigan. This report can also be accessed on Prof. Joyojeet Pal’s blog<\/a>. This is an ongoing research thread, please keep an eye out for updates.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

We examined the use of Twitter by 10426 politicians from Uttar Pradesh, across all levels of seniority, midway into the phases of polling in the Uttar Pradesh elections of 2022, starting January 1, 2022, and up until March 1, 2022. We summarize here our key findings by examining four key questions. How does Twitter relate to Urbanization and Literacy? To address the first question, we examined the number of urban residents by location, and levels of literacy, and find there is a statistically significant relationship between both the number (and percentage) or urban residents and the likelihood that politicians in that area use Twitter, as well as with the level of literacy and the likelihood of tweeting. We removed Lucknow district from the equations we ran, since it is an outlier being the capital where most parties have a number of listed post holders. We see some variation \u2014 for instance, the district with the highest urban populations \u2013 Ghaziabad, adjoining Delhi, and Kanpur, both have fewer politicians online than Varanasi, the Prime Minister\u2019s constituency, which has had a lot of mid- to lower-level politicians go online, and Allahabad \/ Prayagraj, which is a politically important district in the state, and home to several key politicians from across parties. Taking the number of politicians on Twitter as the dependent variable and the urban population of the district as the independent variable,and found a strong correlation between the 2 with an R value of 0.61. The coefficient \ud835\udefd1 was found to be significantly different from 0 with p < 0.05 (see Appendix Table 1). When we ran the same regression to correlate the percentage of urban residents to the number of politicians active on Twitter, again we found a strong statistically significant (p<0.05) relationship between the two variables with an R value of 0.37. There are outliers. On the lower end, we see that Gautam Buddha Nagar (Noida) has a smaller share of politicians active online (partly because of the cross-listing with Delhi) whereas Gorakhpur, an overwhelming majority rural district has a high number of politicians active on Twitter. This again can be attributed to CM Yogi Adityanath, who contests from the district. Please see Appendix 2 for details. We see the same relationship between the number of literate persons in a district and the number of politicians. The relationship here is the strongest, statistically significant (p<0.05) with an R value of 0.78. Figure 3 below shows us a visualization of the districts. Again, we see that Varanasi is an outlier, for the reasons outlined above. Please see Appendix 3 for details. As a sanity check we ran the same regression on the share of literate persons in a district, we again find a statistically significant relationship (p<0.05) with a strong relationship of rate of literacy with the n of politicians on Twitter at an R value of 0.78. Please see Appendix 4 for details. Where\u2019s the Action? To detail these findings, we detail the data by district. Using a crude method of looking at the number of active politicians and the rate at which they get retweeted, we examined the districts in which one or another party had a clear Twitter dominance. We restricted our analysis to those districts that had 50 or more active politicians online. The districts which had a clear BJP Twitter advantage (where the local networks of politicians on Twitter were larger, at least two of the top three accounts belonged to that party, and the party was more active on social media) were Ghaziabad, Amethi, Mathura, Barabanki, Kaushambi, Gorakhpur. The districts where the Samajwadi Party had a clear advantage were Banda, Fatehpur, Etawah, Prayagraj (Allahabad), and Azamgarh. The districts where the Twitter battles were evenly matched across multiple parties were Kannauj, Ballia, Lucknow, Sultanpur. District(min. 40 active politicians) Code SPPoliticians BJP Politicians Other Party Politicians SP per- politician median Tweet count BJP per- politician median Tweet count Other party per- politician median Tweet count Agra AGR 49 125 52 49 111 179.5 Aligarh ALG 14 51 26 150 82 111 Prayagraj ALH 123 84 59 100 53.5 142 Amethi AMT 15 91 53 58 78 85 Ayodhya AYD 28 74 14 28.5 165 162 Azamgarh AZA 53 15 25 68 141 329 Bahraich BAH 40 23 7 59 102 3 Ballia BAL 26 33 25 165.5 115 131 Balrampur BRP 12 14 24 36 108 212 Banda BAN 25 27 16 105 65 84 Barabanki BAR 26 61 19 40 78 63 Bareilly BRL 33 32 19 34 68 157 Basti BAS 21 76 28 17 120 241.5 Bhadohi BDH 12 32 10 91 119.5 235 Chandauli CHD 14 29 9 21 117 26 Deoria DEO 33 63 17 53 97 69 Etawah ETW 37 15 6 80 94 159 Fatehpur FTH 34 19 7 77.5 130 128 Ghaziabad GZB 23 121 47 118 211 122 Ghazipur GZP 25 40 15 77 83.5 68 Gonda GON 20 47 17 52 120 109 Gorakhpur GOR 34 124 27 88.5 130.5 159 Hapur HAP 7 31 27 44 205 199 Hardoi HAR 21 53 12 59 58 98.5 Hathras HAT 4 17 10 320.5 145 86 Jaunpur JNP 66 100 43 90 84.5 145 Jhansi JHA 26 28 26 48.5 177.5 93.5 Kannauj KAN 26 26 8 109 102 97.5 Kanpur Dehat KND 15 16 6 29 288.5 283 Kanpur Nagar KNN 58 81 24 63 136 74.5 Kaushambi KAU 7 30 7 50 138 150 Lucknow LCK 442 406 226 113.5 158 147.5 Mathura MAT 12 53 38 19.5 89 102.5 Meerut MRT 21 77 38 96 137 197 Mirzapur MIR 17 39 20 56 41 109.5 Moradabad MOR 27 48 14 32 80.5 92 Muzaffarnagar MUZ 13 26 30 56 213 144.5 Pratapgarh PGH 22 44 14 96.5 75 19 Rampur RAM 11 29 14 28 103 80 Saharanpur SAH 13 42 20 60 137.5 185 Shahjahanpur SHJ 15 23 12 26 85 127.5 Sitapur SIT 24 28 14 28 123 144.5 Sonbhadra SON 10 37 12 34.5 230 500.5 Sultanpur SUL 24 30 16 30 81 101.5 Unnao UNN 16 32 8 59.5 34.5 148.5 Varanasi VAR 87 137 74 69 111 162.5 Table 1: Key Districts (minimum 40 active politicians on Twitter online) with the number of politicians or political workers identified, and the median rates of retweets (of original tweets) for the period 2021-01-01 to 2022-03-01. These data points may be skewed by the effectiveness of IT cells or small cores of supporters. It is also true that the INC\u2019s IT cell is fairly well organized and networked, but most on-the-ground analyses seem to discount its likelihood of winning seats proportionate to its social media footprint. However, these data underline the massive dominance that the BJP has over other parties on Twitter. District Code Top most followed active state politician handle from the district Party 2nd most followed active state politician handle from the district Party 3rd most followed active state politician handle from the district Party JAL Rashmipal_86 SP bpsvermaoffice BJP mohammad_ubaid_ INC LAL ArchanaPatelAD APNA inckuldeepnsui INC nitinpanthltp BJP HAM DipakSurjeet SP Aryan_Vaishnav9 INC arunodayINC INC KSH RadheshyaSingh SP Sunny10113594 BJP Bjp4shubhamsahi BJP ETA ashishyadavmla SP visheshYSP SP AsRathoreBJP BJP CHK BhaironMishra BJP KishanGupta_INC INC AtuleshanandM BJP FRZ DrChandrasenBJP BJP Prashan25958727 SP RohitYadav5500 SP GBN satender_awana BJP Sandeepsharmak7 BJP AshuChhawri1717 BJP BAH NitishRastogi01 BJP Shivafauji BJP nishanktripath1 BJP MAH yadavyogi1 SP ManojA2Y SP Neerajbuddh_ASP BSP KAS inderveshverma BJP ABVPVikas89 BJP TejendraLodhi BJP AUR AAPlogical AAP manju27bjp BJP Narendralodh73 BJP BRL sachink71656735 BJP JabirAkhtarKhan AIMIM DrPramendr BJP AMR SatyadeoPawar BJP VishalVermaJi00 BJP kstanwarmp BJP HAP anandktrbjp BJP ramesh4Churu BJP SarswatPrafful BJP KAN dineshsngyadav SP poonamy49617468 SP socialistarchna SP BIJ Ashokkatariya9 BJP Digvija27100456 BJP BRBJPBIJNOR BJP KND Up32Wale BJP iABHIKSHA BJP AnkitSinghZ BJP HAT SharadBJPoffice BJP islamkhan919 SP RamAvtarValmiki INC BAS pal_jagdambika BJP Shweta4Nation BJP BajrangbaliMa BJP BAN Shubham41489417 BJP HariNMishra BJP AAPkaRamGupta AAP BRP Dr_Mannan_ AIMIM HKhan_293 INC Vibhuonline INC AZA amitydvsp SP IamShaikhAdil AIMIM NishantRaii SP BDH ashutoshgyanpur BJP AkashDubeyBJP BJP ratnakarbjp BJP HAR jeetusp SP bjpsaurabh12 BJP PrachiPretesh BJP FTH MahipalMahla BJP anjuydv SP YunusSamajwadi SP GON gopalkagarwal BJP KVSinghMPGonda BJP BNSinghbobby BJP ALG SatishGautamBJP BJP kuldeepgaurBjp BJP LakhendraMeena INC AMT DeepakSinghINC INC BJP4Amethi BJP dtripathi264 BJP MAI spsunilyadav SP LalitMYOfficial SP Samajwadi_mpi SP CHD DrMNPandeyMP BJP mlasadhanasingh BJP IshanMilki SP JHA Socialist_arun SP AnuraagJhansi BJP pradeepjain52 INC GZP Virendra_mla SP manvendrabjp BJP rajeshysp SP GOR myogiadityanath BJP AgrawalRMD BJP kamleshpassi67 BJP KAU BJPVinodSonkar BJP BabluGargBjp BJP prashant3k1 BJP BAR priyankaMP_BBK BJP upendrasinghMP BJP PushpendraBjpKm BJP DEO manishagautamak BSP msirsiwal INC BirendraYdvSP SP AMB mpriteshpandey BSP ankitchandelbjp BJP 12tiwari25 AAP AGR BjpRajora BJP AbhilashaBJP BJP Rajkumarchahar9 BJP MAI yadavakhilesh SP SubratPathak12 BJP RanjeetYadavSP1 SP BAL sparvindgiri SP upendratiwari_ BJP virendramastmp BJP AYD pawanpandeysp SP LalluSinghBJP BJP PanditSamarjee2 SP KNN sdPachauri1 BJP ptopmishra SP manojku72692521 SP BAG Phulesavitribai KBMP AnilTomarBjp BJP RLD_Baghpat RLD ALH Vndnason AAP yogita_singh13 SP RakshaMantri SP ETW socialistaditya SP kuwarprashant SP Samajwadi_AY SP JNP YRBSamajwadi SP OsamaShaikhIND INC Hb_o12 BJP GZB Gen_VKSingh BJP druditatyagi BJP preeti_chobey SP LCK CMOfficeUP BJP BJP4UP BJP samajwadiparty SP Table 2: Top three most followed active Twitter accounts by district (minimum 40 active politicians on Twitter online) for the period 2021-01-01 to 2022-03-01. Who does the party think gets the votes, Modi or Yogi? We examined the number of tweets that referred to Narendra Modi and Yogi Adityanath to get a sense of who the party expects will win the elections. The results show that while Yogi Adityanath had a higher footprint early in the campaign in January, that got replaced by Modi by February, to the point where Modi is now consistently the more featured of the two leaders in terms of both the engagement by party politicians and workers, and equally importantly, by the party\u2019s main social media handle. We also checked for this pattern in the main handle for the BJP in the state \u2013 @bjp4UP. Here, we see that Modi was virtually missing from the discourse in much of January, and re-emerged only in February, and since mid-February has in fact been more important in the party\u2019s outreach than the Chief Minister. We visualized the words that appeared most commonly in the tweets of that included @narendramodi and @myogiadityanath during the study period, excluding common tweets and we found that the co-occurring tweets tell a very interesting story about the way BJP leaders and the party establishment sees the two figures in its outreach. To arrive at these, we merged synonyms (thus \u0938\u092a\u093e is merged with \u0938\u092e\u093e\u091c\u0935\u093e\u0926\u0940), we remove common words articles, common verbs (thus \u092e\u0947\u0902, \u0936\u094d\u0930\u0940, \u0914\u0930, \u0939\u0948 etc) as well as words that are purely informational (\u091a\u0941\u0928\u093e\u0935, \u091c\u0928\u0938\u092d\u093e, \u092e\u0924\u0926\u093e\u0928, \u0938\u0924\u094d\u0924\u093e etc) and words that have no political consequence in the context of the tweets (\u092a\u094d\u0930\u0926\u0947\u0936, \u0932\u094b\u0917 etc), and are left with terms that are either explicitly part of the political discourse, or are about locations of relevance. We can see that the differences between the two leaders and the tweets mentioning them are significant. While there are common themes (Kisan, Garib, Vikas) we can see that there are two striking differences. First there are differences in the locations that the two sets of tweets mention Saharanpur, Kashi (his constituency), the Yogi-centric tweets mention Gorakhpur (his constituency), Ayodhya, Muzaffarnagar. Second, we see that the Modi-centric tweets take aim at the familial continuity of power (through the use of \u201cparivarvaad\u201d) \u2013 aimed at both Akhilesh and Priyanka, but primarily at the former. While both leaders refer to farmers, they are a lot more central to Modi-centric messaging. Likewise while \u201cCorona\u201d and \u201cVaccine\u201d also on tweets about both leaders, the centrality of vaccine success, as well as the touting of marquee initiatives like Atmanirbhar are more seen in Modi-centric messaging. Finally, the Yogi-centric messaging has one overarching theme \u2014 that of sectarianism. We see a number of terms either referring to Samajwadi party in veiled references to rioters, terrorists and criminals through the use of terms like \u0905\u092a\u0930\u093e\u0927\u093f\u092f\u094b\u0902, \u0906\u0924\u0902\u0915\u093f\u092f\u094b\u0902, \u092e\u093e\u092b\u093f\u092f\u093e, \u0926\u0902\u0917\u093e\u0907\u092f\u094b\u0902, \u0938\u0941\u0930\u0915\u094d\u0937\u093e but in addition, the Yogi-centric tweets are…<\/p>\n","protected":false},"author":105,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":true,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[1551],"tags":[1548,1542,1549,1550],"class_list":["post-5382","post","type-post","status-publish","format-standard","hentry","category-up-elections-2022","tag-social-media","tag-twitter","tag-uttar-pradesh","tag-uttar-pradesh-elections-2022"],"_links":{"self":[{"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5382","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/users\/105"}],"replies":[{"embeddable":true,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5382"}],"version-history":[{"count":4,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5382\/revisions"}],"predecessor-version":[{"id":5395,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5382\/revisions\/5395"}],"wp:attachment":[{"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5382"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5382"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/precog.iiit.ac.in\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5382"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}